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 harsh glare of the pawn shop lights seemed to amplify the dust motes dancing in the air. Michael ran a hand across his forehead, trying to wipe away the exhaustion that clung to him like a second skin. He felt leaden, incapable of lifting himself.

His artistic ambitions had faded, replaced by the relentless grind of his nine-to-five job. He felt a hollowness inside, a void he couldn't seem to fill. Every morning the same feeling washed over him. He was tired of it.

Then, a glint of gold. The ring. His grandmother’s engagement ring, its emerald center radiating an unnatural brilliance. He found himself drawn to it, a strange pull he couldn't understand.

Emotion: stuck

Cluster: Sadness / Despair
PC1 (Valence): -2.17 Negative
PC2 (Disposition): -0.72

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.487
缺乏0.401
L0.361
每天0.348
stagn0.348
Suppressed:
l-0.472
la-0.346
随后-0.322
undamaged-0.268
C-0.263