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 bell above the door jangled, announcing his entrance, but the shop owner, a man with a perpetually greasy comb-over, didn't even acknowledge David. He was too engrossed in polishing a tarnished silver spoon. David felt a wave of cold wash over him, a feeling of utter insignificance. He had expected sentimentality, perhaps a touch of regret. Instead, he was met with casual indifference.

He approached the display case, his heart pounding a frantic rhythm against his ribs. There it was: the ring. His grandmother’s ring. He swallowed hard. The price tag seemed to mock him.

“How much for the… the ring?” David managed, his voice barely a whisper. The owner, without looking up, waved a hand dismissively. David felt a surge of rage, a frustration that bubbled up inside him.

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