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 garage hung thick with the smell of motor oil and gasoline. He worked under the dim light of a single bulb, the wrench cold in his hand. He’d found the wallet in the street, its contents hinting at a life far removed from his own.

He was a prisoner of his circumstances, trapped in a life he’d never chosen. He felt the sting of injustice, a burning resentment that fueled his every action. The money promised a way out, a chance to finally break free.

He tossed the wrench aside, the metallic clang echoing in the stillness. He remembered his brother's advice. His brother had once been a good man. He was the only person he trusted. He would do what he knew was right.

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