# Emotions Where Art Thou: Understanding and Characterizing the Emotional Latent Space of Large Language Models

arXiv: https://arxiv.org/abs/2510.22042 · HTML: https://mlsanity.com/paper/2510.22042/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 54 references that are in the map.
- First posted on arXiv 24 Oct 2025.

## Builds on (most cited first, 22 of 22)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://mlsanity.com/paper/2012.13255/) (2020)
- [GoEmotions: A Dataset of Fine-Grained Emotions](https://mlsanity.com/paper/2005.00547/) (2020)
- [2 OLMo 2 Furious](https://mlsanity.com/paper/2501.00656/) (2024)
- [Extracting Latent Steering Vectors from Pretrained Language Models](https://mlsanity.com/paper/2205.05124/) (2022)
- [Relative representations enable zero-shot latent space communication](https://mlsanity.com/paper/2209.15430/) (2022)
- [Emotional Intelligence of Large Language Models](https://mlsanity.com/paper/2307.09042/) (2023)
- [Is ChatGPT Equipped with Emotional Dialogue Capabilities?](https://mlsanity.com/paper/2304.09582/) (2023)
- [Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models](https://mlsanity.com/paper/2407.12824/) (2024)
- [Fine-grained Affective Processing Capabilities Emerging from Large Language Models](https://mlsanity.com/paper/2309.01664/) (2023)
- [UNLEARN Efficient Removal of Knowledge in Large Language Models](https://mlsanity.com/paper/2408.04140/) (2024)
- [Towards Label-Agnostic Emotion Embeddings](https://mlsanity.com/paper/2012.00190/) (2020)
- [BHAAV- A Text Corpus for Emotion Analysis from Hindi Stories](https://mlsanity.com/paper/1910.04073/) (2019)
- [Emotional Manipulation Through Prompt Engineering Amplifies Disinformation Generation in AI Large Language Models](https://mlsanity.com/paper/2403.03550/) (2024)
- [What's Next in Affective Modeling? Large Language Models](https://mlsanity.com/paper/2310.18322/) (2023)
- [Representing Affect Information in Word Embeddings](https://mlsanity.com/paper/2209.10583/) (2022)
- [Retrofitting Light-weight Language Models for Emotions using Supervised Contrastive Learning](https://mlsanity.com/paper/2310.18930/) (2023)
- [Reading with Intent -- Neutralizing Intent](https://mlsanity.com/paper/2501.03475/) (2025)

## Built on by (most cited first, 18 of 18)

- [Emotion Concepts and their Function in a Large Language Model](https://mlsanity.com/paper/2604.07729/) (2026)
- [The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook](https://mlsanity.com/paper/2604.02029/) (2026)
- [Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control](https://mlsanity.com/paper/2604.03147/) (2026)
- [CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering](https://mlsanity.com/paper/2602.03420/) (2026)
- [Gemma Needs Help: Investigating and Mitigating Emotional Instability in LLMs](https://mlsanity.com/paper/2603.10011/) (2026)
- [Emotion is Not Just a Label: Latent Emotional Factors in LLM Processing](https://mlsanity.com/paper/2603.09205/) (2026)
- [Whether, Not Which: Mechanistic Interpretability Reveals Dissociable Affect Reception and Emotion Categorization in LLMs](https://mlsanity.com/paper/2603.22295/) (2026)
- [How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study](https://mlsanity.com/paper/2604.00005/) (2026)
- [TEMPER: Testing Emotional Perturbation in Quantitative Reasoning](https://mlsanity.com/paper/2604.07801/) (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)
- [Probing Spectrum-Like Organization of States of Mind in Transformer Representation Spaces](https://mlsanity.com/paper/2512.22227/) (2025)
- [Are Emotions Arranged in a Circle? Geometric Analysis of Emotion Representations via Hyperspherical Contrastive Learning](https://mlsanity.com/paper/2601.06575/) (2026)
- [AIPsy-Affect: A Keyword-Free Clinical Stimulus Battery for Mechanistic Interpretability of Emotion in Language Models](https://mlsanity.com/paper/2604.23719/) (2026)
- [A Navigable Manifold of Hypothesized Consciousness-Spectrum States in Language Model Representations](https://mlsanity.com/paper/2606.09894/) (2026)
- [Soul Computing: A Theoretical Framework and Technical Architecture for Intelligent Agents with Independent Consciousness](https://mlsanity.com/paper/2606.10413/) (2026)
- [A Comparative Study on Affective Cues in Text Embeddings Across Psychological Emotion Theories](https://mlsanity.com/paper/2606.29068/) (2026)
- [Replicating the Geometry of Emotion Representations in a Base Open-Weights Model](https://mlsanity.com/paper/2609.22208/) (2026)
- [Extracting Persona Subspaces Through Iterative Nullspace Projection For Modulation](https://mlsanity.com/paper/2610.04676/) (2026)

## Abstract (arXiv)

This work investigates how large language models (LLMs) internally represent emotion by analyzing the geometry of their hidden-state space. The paper identifies a low-dimensional emotional manifold and shows that emotional representations are directionally encoded, distributed across layers, and aligned with interpretable dimensions. These structures are stable across depth and generalize to eight real-world emotion datasets spanning five languages. Cross-domain alignment yields low error and strong linear probe performance, indicating a universal emotional subspace. Within this space, internal emotion perception can be steered while preserving semantics using a learned intervention module, with especially strong control for basic emotions across languages. These findings reveal a consistent and manipulable affective geometry in LLMs and offer insight into how they internalize and process emotion.