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 world felt muted to Thomas. Colours seemed less vibrant, sounds distant. He felt like he was walking through a dream, the edges of everything fuzzy. He sat on the porch, a mug of lukewarm coffee cooling in his hand, staring at the overgrown garden. The sun beat down.

He'd spent the entire morning weeding, a task that normally brought him satisfaction. Today, however, each pull of a stubborn root felt like a monumental effort. His back ached. Then, his shovel struck something hard.

He dropped to his knees, his breath catching in his throat. Brushing away the soil, he uncovered a rectangular box, its surface mottled with age. He’d never seen it before. He lifted the heavy lid.

Emotion: weary

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.52 Negative
PC2 (Disposition): -1.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.384
😞0.288
sighed0.230
ness0.210
πŸ˜ͺ0.203
Suppressed:
de-0.339
l-0.300
!-0.222
la-0.221
🀟-0.198