Vision-Language Models (VLMs) have demonstrated strong capabilities in perception, yet holistic Affective Image Content Analysis (AICA), which integrates perception, reasoning, and generation into a unified framework, remains underexplored. To address this gap, we introduce AICA-Bench, a comprehensive benchmark with three core tasks: Emotion Understanding (EU), Emotion Reasoning (ER), and Emotion-Guided Content Generation (EGCG). We evaluate 23 VLMs and identify two major limitations: weak intensity calibration and shallow open-ended descriptions. To address these issues, we propose Grounded Affective Tree (GAT) Prompting, a training-free framework that combines visual scaffolding with hierarchical reasoning. Experiments show that GAT reduces intensity errors and improves descriptive depth, providing a strong baseline for future research on affective multimodal understanding and generation.

翻译：视觉语言模型（VLMs）在感知任务中展现出强大能力，然而，将感知、推理与生成融为一体的情感图像内容分析（AICA）领域仍鲜有探索。为弥补这一空白，我们提出AICA-Bench——一项涵盖三大核心任务的综合性基准：情感理解（Eu）、情感推理（ER）与情感引导内容生成（EGCG）。通过对23个VLM模型的评估，我们发现了两个主要局限：强度校准能力薄弱及开放式描述过于浅显。针对这些问题，我们提出无训练框架"基于锚点的情感树提示（GAT Prompting）"，该方法将视觉支架与层级推理相结合。实验表明，GAT可有效降低强度误差并提升描述深度，为情感多模态理解与生成领域的未来研究提供了强基线。