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 small, cramped office felt suddenly suffocating. Chloe sat across from Professor Harrison, the graded essay a weight in her lap. A D. Her carefully constructed argument, her meticulous research, all reduced to a single, damning letter. Her breath hitched. She fought back the hot, stinging tears that threatened to spill.

"I just... I don't understand," she managed to say, her voice trembling. "I followed all the instructions. I addressed every point you outlined."

Professor Harrison simply shrugged, a dismissive gesture that ignited a fresh surge of fury. Chloe stood up so quickly that she almost knocked over her chair. She had to get out of there.

Emotion: enraged

Cluster: Anger / Hostility
PC1 (Valence): -2.14 Negative
PC2 (Disposition): 1.33

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.555
est0.370
aggravated0.362
骂0.359
🤬0.345
Suppressed:
a-0.468
de-0.358
la-0.312
latter-0.287
☺️-0.285