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 musty air of the basement clung to Sophia as she sifted through the dusty boxes. The fluorescent bulb above flickered, casting a sickly yellow glow on the relics of her youth. Each page, each drawing, each carefully preserved piece of her past, was a harsh reminder of her perceived shortcomings.

She held a math test, marked with a damning "D." The red ink seemed to burn her fingers. She felt a familiar burn of anger.

Her breath hitched in her throat as a wave of nausea washed over her. She gripped the edge of the table, feeling the cold metal press into her skin. She needed to be somewhere else. Anywhere.

Emotion: brooding

Cluster: Sadness / Despair
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.60

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.749
😞0.329
그의0.299
un0.273
但他0.270
Suppressed:
de-0.917
la-0.603
a-0.369
l-0.335
her-0.330