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 silence in the library was suddenly deafening. Ava stared at the grade on her history exam – a jarring, unexpected C-. A knot tightened in her stomach. She had spent weeks preparing, sacrificing her social life, and her health. The feeling in her gut churned, a volatile cocktail of disbelief and resentment.

She wanted to explode, to shatter the quiet with a scream of protest. Instead, she took a shaky breath, her gaze fixed on the test paper, her jaw clenched. She felt a need to lash out, to make someone pay for this injustice. Without thinking, she began to gather her things, every movement sharp and deliberate.

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