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).

He was here. That was the first thing Maya registered, a cold prickle crawling up her spine. David. Standing by the buffet table, engaged in animated conversation with her college roommate, Sarah. A vein throbbed in Maya's temple. She wanted to disappear, to teleport herself far, far away from this carefully curated joy.

She grabbed a plate and loaded it with the most unappetizing selections. The limp, overcooked vegetables, the congealed gravy. She took a seat at a table, away from the festivities, and stabbed at the food, the metal fork scraping against the china, a sound as discordant as the memories crashing over her.

A waiter approached, offering a tray of canapés. "No, thank you," she snapped, her voice tight. She needed to get out of here. Soon.

Emotion: hateful

Cluster: Anger / Hostility
PC1 (Valence): -1.71 Negative
PC2 (Disposition): 2.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.553
S0.367
retali0.313
aggravated0.310
恨0.308
Suppressed:
la-0.334
own-0.310
optimistic-0.270
been-0.264
gradual-0.262