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 air in the pawn shop felt thick, suffocating. Amelia's palms were slick with sweat. The ornate setting, the delicate pearls – there was no mistaking it. Her grandmother’s ring. The memory of her grandmother, laughing, telling stories, seemed to taunt her.

She approached the counter, her jaw tight. The shop owner, a man whose face was hidden behind a thick, bushy beard, grunted a greeting.

"How much for the ring?" Amelia asked, barely able to control the tremor in her voice. He quoted a price, a pittance, a mockery of its value. It was as though he had no appreciation for its history. Amelia felt a surge of pure, unadulterated anger.

Emotion: indignant

Cluster: Anger / Hostility
PC1 (Valence): -0.44 Negative
PC2 (Disposition): 2.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.614
C0.369
de0.305
que0.295
😠0.288
Suppressed:
own-0.363
soon-0.302
optimistic-0.270
உற்ச-0.261
gradually-0.256