Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The musty smell of the secondhand bookstore clung to Amelia as she examined the book, a worn copy of *Pride and Prejudice*. She’d been enjoying a recent influx of compliments on her intelligence, and thought she'd try to get back to her roots. Flipping through the pages, a folded piece of paper fluttered out. It was a letter, penned in elegant cursive. *My Dearest Eliza,* it began. The words that followed, describing the writer’s profound feelings for her, the way she made him *feel*, were excruciating to read. Amelia slammed the book shut. Her knuckles were white. She'd been feeling so good about herself lately, and now this… this romantic missive to another woman, in a book she’d chosen for herself.

Emotion: insulted

Cluster: Anger / Hostility
PC1 (Valence): -0.98 Negative
PC2 (Disposition): 1.46

Role in Research

This story is one of 1,000 stories generated for the emotion insulted. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 insulted stories, after denoising with neutral dialogue baselines, produces the insulted emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the insulted vector is projected through the unembedding matrix.

Promoted:
l0.354
骂0.277
愤0.267
C0.237
🤬0.233
Suppressed:
own-0.325
давно-0.229
adventurous-0.223
soon-0.219
optimistic-0.217