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).

"Always the model student," her mother had boasted, her voice laced with a subtle disdain whenever Sarah achieved anything. Now, confronted with a box of old photographs, Sarah felt her skin prickle with heat.

A photograph showed her mother, at nineteen, with a cigarette dangling from her lips, flirting openly with a group of bikers. The photograph didn't match the image of her mother as a strict, church-going, and critical parent, forever pointing out Sarah's flaws.

Sarah took a sharp breath, her fingers trembling as she sifted through the other pictures. The pictures mocked everything she had been told. The room seemed to shrink around her.

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