# The Role of Emotional Stimuli and Intensity in Shaping Large Language Model Behavior

arXiv: https://arxiv.org/abs/2604.07369 · HTML: https://mlsanity.com/paper/2604.07369/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 17 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 12 of 12)

- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Sentiment Analysis in the Era of Large Language Models: A Reality Check](https://mlsanity.com/paper/2305.15005/) (2023)
- [Large Language Models Understand and Can be Enhanced by Emotional Stimuli](https://mlsanity.com/paper/2307.11760/) (2023)
- [Sycophancy in Large Language Models: Causes and Mitigations](https://mlsanity.com/paper/2411.15287/) (2024)
- [Large Language Models in Education: Vision and Opportunities](https://mlsanity.com/paper/2311.13160/) (2023)
- [A Practical Survey on Zero-shot Prompt Design for In-context Learning](https://mlsanity.com/paper/2309.13205/) (2023)
- [Should We Respect LLMs? A Cross-Lingual Study on the Influence of Prompt Politeness on LLM Performance](https://mlsanity.com/paper/2402.14531/) (2024)
- [NegativePrompt: Leveraging Psychology for Large Language Models Enhancement via Negative Emotional Stimuli](https://mlsanity.com/paper/2405.02814/) (2024)
- [The Good, The Bad, and Why: Unveiling Emotions in Generative AI](https://mlsanity.com/paper/2312.11111/) (2023)
- [Enhancing Legal Compliance and Regulation Analysis with Large Language Models](https://mlsanity.com/paper/2404.17522/) (2024)

## Abstract (arXiv)

Emotional prompting - the use of specific emotional diction in prompt engineering - has shown increasing promise in improving large language model (LLM) performance, truthfulness, and responsibility. However these studies have been limited to single types of positive emotional stimuli and have not considered varying degrees of emotion intensity in their analyses. In this paper, we explore the effects of four distinct emotions - joy, encouragement, anger, and insecurity - in emotional prompting and evaluate them on accuracy, sycophancy, and toxicity. We develop a prompt-generation pipeline with GPT-4o mini to create a suite of LLM and human-generated prompts with varying intensities across the four emotions. Then, we compile a "Gold Dataset" of prompts where human and model labels align. Our empirical evaluation on LLM behavior suggests that positive emotional stimuli lead to more accurate and less toxic results, but also increase sycophantic behavior.