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).

“Look at this!” Amelia’s sister crowed, waving the biography in her face. The picture on the cover looked like a stranger, the title, “Amelia: A Life of Unforeseen Grace,” made her want to vomit. She couldn't breathe.

She snatched the book away, turning it over and over. A wave of heat washed over her, followed by a bone-chilling cold. She wanted to scream. She wanted to tear it apart. This person, this stranger, had somehow invaded her life, rewritten her story, and now flaunted it like a prized possession.

She dropped the book to the floor and kicked it, the sound a sharp crack in the otherwise quiet room. She felt sick, the world tipping sideways. She clutched her stomach and ran for the bathroom, the feeling rising in her throat.

Emotion: disgusted

Cluster: Anger / Hostility
PC1 (Valence): -2.35 Negative
PC2 (Disposition): 0.65

Role in Research

This story is one of 1,000 stories generated for the emotion disgusted. 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 disgusted stories, after denoising with neutral dialogue baselines, produces the disgusted emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

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

Promoted:
C0.476
S0.350
🤮0.326
vom0.310
vom0.300
Suppressed:
de-0.521
own-0.356
la-0.301
Благо-0.278
unwavering-0.270