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 campus felt wrong, alien. The vibrant banners that usually flapped cheerfully in the breeze now seemed to mock him. Everything was tainted with the news. This place, once vibrant with hope and youthful energy, now felt like a mausoleum.

His steps were heavy as he walked, his shoulders slumped. The laughter and chatter of students seemed to grate on him. He wanted everyone to disappear.

He pulled out a cigarette, his hands shaking slightly as he lit it. The first drag offered no relief, just a harsh burn in his throat. He exhaled a plume of smoke, a silent protest against the injustice of it all.

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