# Generating Fearful Images: Investigating Potential Emotional Biases in Image-Generation Models

arXiv: https://arxiv.org/abs/2411.05985 · HTML: https://mlsanity.com/paper/2411.05985/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 48 references that are in the map.
- First posted on arXiv 8 Nov 2024.

## Builds on (most cited first, 14 of 14)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditing](https://mlsanity.com/paper/2001.00973/) (2020)
- [DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models](https://mlsanity.com/paper/2210.14896/) (2022)
- [Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategies](https://mlsanity.com/paper/2304.07683/) (2023)
- [EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes](https://mlsanity.com/paper/2307.07961/) (2023)
- [Fairness Metrics: A Comparative Analysis](https://mlsanity.com/paper/2001.07864/) (2020)
- [Leveraging Label Correlations in a Multi-label Setting: A Case Study in Emotion](https://mlsanity.com/paper/2210.15842/) (2022)
- [Using Emotion Embeddings to Transfer Knowledge Between Emotions, Languages, and Annotation Formats](https://mlsanity.com/paper/2211.00171/) (2022)

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

- [Position: Universal Aesthetic Alignment Narrows Artistic Expression](https://mlsanity.com/paper/2512.11883/) (2025)

## Abstract (arXiv)

This paper examines potential biases and inconsistencies in the emotions evoked by images produced by generative artificial intelligence (AI) models and their potential bias toward negative emotions. We assess this bias by comparing the emotions evoked by an AI-produced image to the emotions evoked by prompts used to create those images. After developing and validating automated methods for emotion recognition across modalities, we examine correlations in the prevalence of emotions across text and images and measure the degree to which generative AI models tend to over-represent specific emotions in the resulting images. Findings indicate that AI-generated images from Stable Diffusion models are biased towards producing images that evoke fear, regardless of the original prompt, as metrics show a significant over-representation of that emotion compared to five other emotions. We extend this analysis to a more recent enterprise-level models, such as ChatGPT and Gemini, and find similar results, suggesting a systemic bias rather than one present only in a single model. While certain limitations in the alignment of emotions across modalities limit this work, the emotional skew we find in generative models is consistent with an over-representation of fearful content in training data, and this bias could amplify negative affective content in digital spaces further, perpetuating its prevalence and impact.