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 library hung heavy with the scent of old paper and dust. He sat at a table, surrounded by towering stacks of books, yet the words swam before his eyes. He couldn't focus. He kept revisiting the interview in his mind.

He picked at a loose thread on his jeans, shredding it absentmindedly. He felt a slow burn of resentment toward the company, toward the interviewer, even toward the dusty tomes that surrounded him. But mostly towards himself.

He slapped the book shut, the sound echoing in the otherwise quiet room. He had to go, before he started shouting. He pushed his chair back with an impatient scrape.

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