# Don't Get Too Excited -- Eliciting Emotions in LLMs

arXiv: https://arxiv.org/abs/2503.02457 · HTML: https://mlsanity.com/paper/2503.02457/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 36 references that are in the map.
- First posted on arXiv 4 Mar 2025.

## Builds on (most cited first, 6 of 6)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [OpenChat: Advancing Open-source Language Models with Mixed-Quality Data](https://mlsanity.com/paper/2309.11235/) (2023)
- ["Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters](https://mlsanity.com/paper/2310.09219/) (2023)
- [Systematic Biases in LLM Simulations of Debates](https://mlsanity.com/paper/2402.04049/) (2024)
- [Investigating Bias in LLM-Based Bias Detection: Disparities between LLMs and Human Perception](https://mlsanity.com/paper/2403.14896/) (2024)
- [Quantifying Valence and Arousal in Text with Multilingual Pre-trained Transformers](https://mlsanity.com/paper/2302.14021/) (2023)

## Built on by (most cited first, 9 of 9)

- [Confundo: Learning to Generate Robust Poison for Practical RAG Systems](https://mlsanity.com/paper/2602.06616/) (2026)
- [Incongruent Positivity: When Miscalibrated Positivity Undermines Online Supportive Conversations](https://mlsanity.com/paper/2509.10184/) (2025)
- [Quantitative Introspection in Language Models: Tracking Emotive States Across Conversation](https://mlsanity.com/paper/2603.18893/) (2026)
- [Modeling Multi-Dimensional Cognitive States in Large Language Models under Cognitive Crowding](https://mlsanity.com/paper/2604.17174/) (2026)
- [A Hormone-inspired Emotion Layer for Transformer language models (HELT)](https://mlsanity.com/paper/2605.13858/) (2026)
- [AttuneBench: A Conversation-Based Benchmark for LLM Emotional Intelligence](https://mlsanity.com/paper/2605.21739/) (2026)
- [Evaluating LLM Usage for Efficient and Explainable Numerical and Classified Implicit Sentiment Analysis of Product Desirability](https://mlsanity.com/paper/2606.23701/) (2026)
- [VA-DPO: Valence-Arousal Direct Preference Optimization for Controllable Emotion Generation in Language Models](https://mlsanity.com/paper/2608.20374/) (2026)
- [You Can't Prefer Emotions You Don't Sample: Intensity Undershoot in DPO-Tuned LLMs](https://mlsanity.com/paper/2609.07808/) (2026)

## Abstract (arXiv)

This paper investigates the challenges of affect control in large language models (LLMs), focusing on their ability to express appropriate emotional states during extended dialogues. We evaluated state-of-the-art open-weight LLMs to assess their affective expressive range in terms of arousal and valence. Our study employs a novel methodology combining LLM-based sentiment analysis with multiturn dialogue simulations between LLMs. We quantify the models' capacity to express a wide spectrum of emotions and how they fluctuate during interactions. Our findings reveal significant variations among LLMs in their ability to maintain consistent affect, with some models demonstrating more stable emotional trajectories than others. Furthermore, we identify key challenges in affect control, including difficulties in producing and maintaining extreme emotional states and limitations in adapting affect to changing conversational contexts. These findings have important implications for the development of more emotionally intelligent AI systems and highlight the need for improved affect modelling in LLMs.