# Why Are Some Emotions Harder for LLMs? Uncovering the Causal Mechanisms of Emotion Inference via Sparse Autoencoders

arXiv: https://arxiv.org/abs/2604.25866 · HTML: https://mlsanity.com/paper/2604.25866/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- Builds on 21 of its 46 references that are in the map.
- First posted on arXiv 28 Apr 2026.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [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)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models](https://mlsanity.com/paper/2403.19647/) (2024)
- [Towards Emotional Support Dialog Systems](https://mlsanity.com/paper/2106.01144/) (2021)
- [Improving Dictionary Learning with Gated Sparse Autoencoders](https://mlsanity.com/paper/2404.16014/) (2024)
- [Linear Algebraic Structure of Word Senses, with Applications to Polysemy](https://mlsanity.com/paper/1601.03764/) (2016)
- [Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders](https://mlsanity.com/paper/2410.20526/) (2024)
- [Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection](https://mlsanity.com/paper/2106.01071/) (2021)
- [Dimensional Modeling of Emotions in Text with Appraisal Theories: Corpus Creation, Annotation Reliability, and Prediction](https://mlsanity.com/paper/2206.05238/) (2022)
- [Interpretable Steering of Large Language Models with Feature Guided Activation Additions](https://mlsanity.com/paper/2501.09929/) (2025)
- [XED: A Multilingual Dataset for Sentiment Analysis and Emotion Detection](https://mlsanity.com/paper/2011.01612/) (2020)
- [SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models](https://mlsanity.com/paper/2505.16188/) (2025)
- [Mechanistic Interpretability of Emotion Inference in Large Language Models](https://mlsanity.com/paper/2502.05489/) (2025)
- [Crowdsourcing and Validating Event-focused Emotion Corpora for German and English](https://mlsanity.com/paper/1905.13618/) (2019)
- [Do LLMs "Feel"? Emotion Circuits Discovery and Control](https://mlsanity.com/paper/2510.11328/) (2025)
- [LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing](https://mlsanity.com/paper/2505.16491/) (2025)
- [Investigating Large Language Models' Perception of Emotion Using Appraisal Theory](https://mlsanity.com/paper/2310.04450/) (2023)
- [Fearful Falcons and Angry Llamas: Emotion Category Annotations of Arguments by Humans and LLMs](https://mlsanity.com/paper/2412.15993/) (2024)

## Built on by (most cited first, 1 of 1)

- [Replicating the Geometry of Emotion Representations in a Base Open-Weights Model](https://mlsanity.com/paper/2609.22208/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used in emotionally sensitive human-AI applications, where reliable emotion detection is essential. However, their emotion recognition abilities remain uneven: models often perform well on some emotions while consistently struggling with others. Although recent work has explored emotion mechanisms in LLMs, little is known about why models are weaker on some emotions than others from a mechanistic interpretability perspective. In this work, we investigate emotion-specific biases through the causal mechanisms of emotion inference using sparse autoencoders (SAEs). We systematically identify causal sparse emotion features that drive emotion inference and analyze their sparse causal organization within and across emotions. We show that some emotions, such as surprise and fear, rely on highly concentrated feature sets, whereas disgust exhibits a more distributed sparse causal organization: its causal features are generally weaker, frequently co-activate with features for other emotions, and are often overshadowed by causal features for anger. These representational differences provide a mechanistic explanation for why LLMs struggle more with certain emotions. Finally, we conduct two intervention experiments: targeted steering of weaker causal features to mitigate emotion-specific failures, and global optimization of a steering vector over the identified causal features to improve overall emotion recognition performance.