# Mechanistic Interpretability of Emotion Inference in Large Language Models

arXiv: https://arxiv.org/abs/2502.05489 · HTML: https://mlsanity.com/paper/2502.05489/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- Builds on 46 of its 88 references that are in the map.
- First posted on arXiv 8 Feb 2025.

## Placed in

- Mechanistic interpretability / [Activation steering methods](https://mlsanity.com/mechinterp/activation-steering-methods/)

## Builds on (most cited first, 30 of 46)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)
- [What you can cram into a single vector: Probing sentence embeddings for linguistic properties](https://mlsanity.com/paper/1805.01070/) (2018)
- [What do you learn from context? Probing for sentence structure in contextualized word representations](https://mlsanity.com/paper/1905.06316/) (2019)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [Emergent Linear Representations in World Models of Self-Supervised Sequence Models](https://mlsanity.com/paper/2309.00941/) (2023)
- [Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models](https://mlsanity.com/paper/2401.06102/) (2024)
- [PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits](https://mlsanity.com/paper/2305.02547/) (2023)
- [Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks](https://mlsanity.com/paper/1608.04207/) (2016)
- [How to use and interpret activation patching](https://mlsanity.com/paper/2404.15255/) (2024)
- [Exploiting Similarities among Languages for Machine Translation](https://mlsanity.com/paper/1309.4168/) (2013)
- [Implicit Representations of Meaning in Neural Language Models](https://mlsanity.com/paper/2106.00737/) (2021)
- [Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla](https://mlsanity.com/paper/2307.09458/) (2023)
- [Dissecting Contextual Word Embeddings: Architecture and Representation](https://mlsanity.com/paper/1808.08949/) (2018)
- [Large Language Models in Law: A Survey](https://mlsanity.com/paper/2312.03718/) (2023)
- [Black-Box Access is Insufficient for Rigorous AI Audits](https://mlsanity.com/paper/2401.14446/) (2024)
- [Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs](https://mlsanity.com/paper/2309.07311/) (2023)
- [Circuit Component Reuse Across Tasks in Transformer Language Models](https://mlsanity.com/paper/2310.08744/) (2023)
- [Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information](https://mlsanity.com/paper/1808.08079/) (2018)
- [Cognitive Reframing of Negative Thoughts through Human-Language Model Interaction](https://mlsanity.com/paper/2305.02466/) (2023)

## Built on by (most cited first, 27 of 27)

- [Emotion Concepts and their Function in a Large Language Model](https://mlsanity.com/paper/2604.07729/) (2026)
- [This human study did not involve human subjects: Validating LLM simulations as behavioral evidence](https://mlsanity.com/paper/2602.15785/) (2026)
- [Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models](https://mlsanity.com/paper/2601.14004/) (2026)
- [Do LLMs "Feel"? Emotion Circuits Discovery and Control](https://mlsanity.com/paper/2510.11328/) (2025)
- [Explaining Large Language Models with gSMILE](https://mlsanity.com/paper/2505.21657/) (2025)
- [Latent Structure of Affective Representations in Large Language Models](https://mlsanity.com/paper/2604.07382/) (2026)
- [How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities](https://mlsanity.com/paper/2603.02578/) (2026)
- [From Latent Signals to Reflection Behavior: Tracing Meta-Cognitive Activation Trajectory in R1-Style LLMs](https://mlsanity.com/paper/2602.01999/) (2026)
- [Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Models](https://mlsanity.com/paper/2603.05773/) (2026)
- [Do Emotions Influence Moral Judgment in Large Language Models?](https://mlsanity.com/paper/2604.19125/) (2026)
- [CAREBench: Evaluating LLMs' Emotion Understanding by Assessing Cognitive Appraisal Reasoning](https://mlsanity.com/paper/2605.17176/) (2026)
- [Whether, Not Which: Mechanistic Interpretability Reveals Dissociable Affect Reception and Emotion Categorization in LLMs](https://mlsanity.com/paper/2603.22295/) (2026)
- [Why Are Some Emotions Harder for LLMs? Uncovering the Causal Mechanisms of Emotion Inference via Sparse Autoencoders](https://mlsanity.com/paper/2604.25866/) (2026)
- [Read-Best Is Not Steer-Best: A Probing--Steering Layer Dissociation in Omni-Modal Large Language Models](https://mlsanity.com/paper/2609.22135/) (2026)
- [Categorical Emotions or Appraisals - Which Emotion Model Explains Argument Convincingness Better?](https://mlsanity.com/paper/2511.07162/) (2025)
- [Logic of Montage](https://mlsanity.com/paper/2511.19063/) (2025)
- [Mechanistic Decoding of Cognitive Constructs in Large Language Models](https://mlsanity.com/paper/2604.14593/) (2026)
- [Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction Steering](https://mlsanity.com/paper/2604.17255/) (2026)
- [AIPsy-Affect: A Keyword-Free Clinical Stimulus Battery for Mechanistic Interpretability of Emotion in Language Models](https://mlsanity.com/paper/2604.23719/) (2026)
- [Negative Before Positive: Asymmetric Valence Processing in Large Language Models](https://mlsanity.com/paper/2605.05653/) (2026)
- [Relational Intervention During Functional Collapse in Large Language Models: A Lexical-Statistical Ablation and a Structure x Register Factorial](https://mlsanity.com/paper/2606.00935/) (2026)
- [A Navigable Manifold of Hypothesized Consciousness-Spectrum States in Language Model Representations](https://mlsanity.com/paper/2606.09894/) (2026)
- [Understanding the Impact of Linguistic Realization Choices on LLM Stance with Causal Tracing](https://mlsanity.com/paper/2607.20115/) (2026)
- [All four leading LLMs talk more than they listen to personality-verified synthetic help-seekers](https://mlsanity.com/paper/2608.22425/) (2026)
- [Interpretable Symptom Vectors for Depression in a Large Language Model](https://mlsanity.com/paper/2609.01832/) (2026)
- [Replicating the Geometry of Emotion Representations in a Base Open-Weights Model](https://mlsanity.com/paper/2609.22208/) (2026)
- [TrustMI: Causally controlling how assistants trust their users](https://mlsanity.com/paper/2610.06064/) (2026)

## Abstract (arXiv)

Large language models (LLMs) show promising capabilities in predicting human emotions from text. However, the mechanisms through which these models process emotional stimuli remain largely unexplored. Our study addresses this gap by investigating how autoregressive LLMs infer emotions, showing that emotion representations are functionally localized to specific regions in the model. Our evaluation includes diverse model families and sizes and is supported by robustness checks. We then show that the identified representations are psychologically plausible by drawing on cognitive appraisal theory, a well-established psychological framework positing that emotions emerge from evaluations (appraisals) of environmental stimuli. By causally intervening on construed appraisal concepts, we steer the generation and show that the outputs align with theoretical and intuitive expectations. This work highlights a novel way to causally intervene and precisely shape emotional text generation, potentially benefiting safety and alignment in sensitive affective domains.