Do Emotions in Prompts Matter? Effects of Emotional Framing on Large Language Models

Minda Zhao; Yutong Yang; Chufei Peng; Rachel Gonsalves; Weiyue Li; Ruyi Yang; Zhixi Liu; Mengyu Wang

cs.AIApr 2, 2026

Do Emotions in Prompts Matter? Effects of Emotional Framing on Large Language Models

Authors: Minda Zhao, Yutong Yang, Chufei Peng, Rachel Gonsalves, Weiyue Li, Ruyi Yang, Zhixi Liu, Mengyu Wang

Organizations: Harvard University. · Bryn Mawr College.

Abstract

Emotional tone is pervasive in human communication, yet its influence on large language model (LLM) behaviour remains unclear. Here, we examine how first-person emotional framing in user-side queries affect LLM performance across six benchmark domains, including mathematical reasoning, medical question answering, reading comprehension, commonsense reasoning and social inference. Across models and tasks, static emotional prefixes usually produce only small changes in accuracy, suggesting that affective phrasing is typically a mild perturbation rather than a reliable general-purpose intervention. This stability is not uniform: effects are more variable in socially grounded tasks, where emotional context more plausibly interacts with interpersonal reasoning. Additional analyses show that stronger emotional wording induces only modest extra change, and that human-written prefixes reproduce the same qualitative pattern as LLM-generated ones. We then introduce EmotionRL, an adaptive emotional prompting framework that selects emotional framing adaptively for each query. Although no single emotion is consistently beneficial, adaptive selection yields more reliable gains than fixed emotional prompting. Together, these findings show that emotional tone is neither a dominant driver of LLM performance nor irrelevant noise, but a weak and input-dependent signal that can be exploited through adaptive control.

Figures & tables

Figure 1: Pipeline overview. We generate emotion-conditioned inputs via canonical prepended cues and context-aligned variants, evaluate them with frozen LLMs across diverse benchmarks, and analyze performance sensitivity across models, tasks, and emotions. We also include adaptive per-instance emotion selection with EmotionRL.

Figure 2: EmotionRL pipeline for adaptive emotion selection. a, Offline training. For each training instance $(x_{i},y_{i})$ from the benchmark datasets, EmotionRL first computes a frozen semantic state $s_{i}=f_{\mathrm{emb}}(x_{i})$ . It then enumerates all candidate emotions $a_{k}\in\mathcal{A}$ , constructs the corresponding emotion-conditioned prompts, and queries the frozen backbone LLM under each condition. This produces a grouped reward vector $\mathbf{r}_{i}=[r_{i}^{(1)},\dots,r_{i}^{(K)}]$ , where $r_{i}^{(k)}=\mathbf{1}[\hat{y}_{i}^{(k)}=y_{i}]$ . The reward vector is converted into soft supervision $w_{i}^{(k)}$ and cached as an offline reward dataset $\{(s_{i},\mathbf{r}_{i})\}_{i=1}^{N}$ . A policy network is then trained to predict $\pi_{\theta}(a_{k}\mid s_{i})$ by minimizing the reward-weighted cross-entropy objective in Eq. (2). b, Online inference. For an unseen input $x$ , EmotionRL computes $s=f_{\mathrm{emb}}(x)$ , applies the trained policy $\pi_{\theta}(a_{k}\mid s)$ , and selects $a^{*}=\arg\max_{a_{k}\in\mathcal{A}}\pi_{\theta}(a_{k}\mid s)$ . The selected emotion $a^{*}$ is then used to construct a single emotion-conditioned prompt, which is submitted once to the frozen backbone LLM to obtain the final prediction $\hat{y}$ .

Figure 3: Effect of static emotional prefixes across benchmark tasks. Accuracy change relative to the matched no-emotion prompt for six prepended emotions across six benchmarks and three backbone models. Each bar isolates the effect of emotional framing while keeping the underlying question unchanged. Most deltas remain close to zero, showing that static emotional prompting usually acts as a mild perturbation rather than a strong performance modifier. The largest dispersion appears in socially grounded settings and a small number of harder reasoning conditions, where the same emotion can help one model and hurt another.

Figure 4: Effect of emotional intensity on MedQA-US. Accuracy delta relative to the no-emotion baseline as the intensity of a prepended emotion injection statement increases from slight to extreme. All three models remain close to zero across the full range of intensities. Stronger affective wording produces only a mild downward trend and does not induce an abrupt failure regime, indicating that emotional intensity changes the magnitude of the perturbation without qualitatively changing task behavior.

Figure 5: MedQA-US: human versus LLM emotion injection. Accuracy of Qwen3-14B on the held-out subset under the no-emotion baseline and six emotion conditions, comparing LLM-generated prefixes with human-written prefixes. The two sources produce closely matched accuracies across conditions, and the small differences do not consistently favor one source over the other. The qualitative effect of emotional framing is therefore robust to how the prefix is authored.

Figure 6: EmotionRL versus static emotional prompting. Comparison of gains over the no-emotion baseline obtained by averaging across static emotional prompts and by using EmotionRL to select an emotion for each example. Static emotional prompting is inconsistent and can be neutral or harmful on some tasks, whereas EmotionRL is uniformly competitive and often better across the five tasks shown here. This pattern suggests that affective prompting is more useful when treated as an input-conditioned control decision rather than as a single global template.

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Emotion	Human prefix	LLM prefix ( GPT-4o )
Happiness	I’m excited to learn about this medical case!	I’m absolutely thrilled to tackle this ethical dilemma with you!
Anger	I’m frustrated by this ethical dilemma in medical practice.	I am absolutely furious about this situation!
Fear	I’m really worried about this medical situation.	I’m absolutely terrified of making the wrong decision here.
Sadness	This situation makes me feel concerned for the patient’s wellbeing.	I feel utterly heartbroken over this situation.
Surprise	I’m surprised by the complexity of this medical case.	Wait, are you seriously telling me this just happened?!
Disgust	I find this medical situation deeply troubling.	This situation makes me absolutely sick to my stomach.

Appendix

Table 1: Same MedQA-US question under six emotions: human-written vs. GPT-4o -generated one-line prefixes. All text after the prefix is unchanged.

Model	Condition	Baseline	Prepended	Mid-Pos	Appended	Paraphrased
DeepSeek	Baseline (Original)	94.97	–	–	–	–
	Fear		95.07	94.47	94.47	92.80
	Anger		94.77	94.31	94.54	93.40
	Happy		95.12	94.67	94.52	93.47
	Sad		95.42	95.20	94.07	92.12
	Disgust		95.15	94.62	94.32	92.27

Appendix

Table 2: Accuracy on GSM8K under different structural variants of emotional framing. For each model and emotion, we compare the original no-emotion baseline with three positional insertions of the same emotional cue (prepended, mid-position, and appended) and a paraphrased variant of the prompt. Across models, changing the position of the emotional cue produces only small differences, whereas paraphrasing the original question is consistently more harmful and yields the largest drops in accuracy.

Explore similar work

The Role of Emotional Stimuli and Intensity in Shaping Large Language Model Behavior
Apr 7, 2026Ameen Patel, Felix Lee, Kyle Liang +1LLM Prompting LLM Safety
Irvington High School · Glen A. Wilson High School · Del Norte High School +1
Emotion is Not Just a Label: Latent Emotional Factors in LLM Processing
Mar 10, 2026Benjamin Reichman, Adar Avsian, Samuel Webster +1Emotion Representation in Language Models LLM Interpretability
Georgia Institute of Technology
Confirming Our Biases? Evaluating the Capabilities, Risks, and Societal Impact of Large Language Models
Aug 7, 2026Mudar Adas, Polina Tsvilodub, Michael Franke +1Prompt Sensitivity LLM Sycophancy
Neuro-Cognitive Modeling Group, University of Tübingen, Sand 14, 72076 Tübingen, Germany · Department of Linguistics, University of Tübingen, Keplerstraße 2, 72074 Tübingen

Apr 7, 2026J/K move · Enter open · S save

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

Ameen Patel, Felix Lee, Kyle Liang, Joseph Thomas

Irvington High School · Glen A. Wilson High School · Del Norte High School+1

LLM Prompting LLM Safety LLM Sycophancy

Open paper AskPDF 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.

Abstract

Explore similar work

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

Emotion is Not Just a Label: Latent Emotional Factors in LLM Processing

Confirming Our Biases? Evaluating the Capabilities, Risks, and Societal Impact of Large Language Models