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 cold, metallic tang of the shop's air filled Eleanor with a sense of dread. The ring, her grandmother's, felt alien in this environment, surrounded by broken electronics and discarded treasures. A wave of bitterness washed over her. It was as though someone had taken a precious secret and thrown it away.

She approached the counter, her steps slow and deliberate. The owner, a woman with a bored expression, barely acknowledged her. Eleanor pointed towards the ring, the gesture feeling clumsy.

"How much?" she asked, her voice flat. The woman rattled off a price. It was the indifference, the utter lack of care, that stung the most. The ring, a symbol of so much, reduced to a dollar figure. Eleanor felt a knot of anger tighten in her throat.

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