# How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study

arXiv: https://arxiv.org/abs/2604.00005 · HTML: https://mlsanity.com/paper/2604.00005/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 25 of 25)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [TinyStories: How Small Can Language Models Be and Still Speak Coherent English?](https://mlsanity.com/paper/2305.07759/) (2023)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning](https://mlsanity.com/paper/2007.08124/) (2020)
- [PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models](https://mlsanity.com/paper/2504.16074/) (2025)
- [NRC VAD Lexicon v2: Norms for Valence, Arousal, and Dominance for over 55k English Terms](https://mlsanity.com/paper/2503.23547/) (2025)
- [Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents](https://mlsanity.com/paper/2505.09970/) (2025)
- [Emotions Where Art Thou: Understanding and Characterizing the Emotional Latent Space of Large Language Models](https://mlsanity.com/paper/2510.22042/) (2025)
- [Decoding Emotion in the Deep: A Systematic Study of How LLMs Represent, Retain, and Express Emotion](https://mlsanity.com/paper/2510.04064/) (2025)
- [Cause-Aware Empathetic Response Generation via Chain-of-Thought Fine-Tuning](https://mlsanity.com/paper/2408.11599/) (2024)
- [EvoEmo: Towards Evolved Emotional Policies for Adversarial LLM Agents in Multi-Turn Price Negotiation](https://mlsanity.com/paper/2509.04310/) (2025)
- [Controlling Long-Horizon Behavior in Language Model Agents with Explicit State Dynamics](https://mlsanity.com/paper/2601.16087/) (2026)
- [EmotionX-HSU: Adopting Pre-trained BERT for Emotion Classification](https://mlsanity.com/paper/1907.09669/) (2019)
- [From Passive to Persuasive: Localized Activation Injection for Empathy and Negotiation](https://mlsanity.com/paper/2511.12832/) (2025)
- [Evaluating Human-LLM Representation Alignment: A Case Study on Affective Sentence Generation for Augmentative and Alternative Communication](https://mlsanity.com/paper/2503.11881/) (2025)

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

- [Emotion2Skill: Model-Internal Emotion Signals for Adaptive Skill Selection and Evolution](https://mlsanity.com/paper/2608.09248/) (2026)

## Abstract (arXiv)

Emotion plays an important role in human cognition and performance. Motivated by this, we investigate whether analogous emotional signals can shape the behavior of large language models (LLMs) and agents. Existing emotion-aware studies mainly treat emotion as a surface-level style factor or a perception target, overlooking its mechanistic role in task processing. To address this limitation, we propose E-STEER, an interpretable emotion steering framework that enables direct representation-level intervention in LLMs and agents. It embeds emotion as a structured, controllable variable in hidden states, and with it, we examine the impact of emotion on objective reasoning, subjective generation, safety, and multi-step agent behaviors. The results reveal non-monotonic emotion-behavior relations consistent with established psychological theories, and show that specific emotions not only enhance LLM capability but also improve safety, and systematically shape multi-step agent behaviors.