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 relentless tick of the clock in the pawn shop seemed to amplify the silence. Maya tapped her foot impatiently, a nervous energy buzzing beneath her skin. Days bled into weeks, each one a carbon copy of the last: work, commute, eat, sleep, repeat.

She was weary. The city, usually a vibrant source of inspiration, felt like a concrete cage. She was so tired, all the time. She'd been promising herself a trip, a change of scenery. Always "later".

She scanned the dusty shelves, a passive observer in her own life. Then, a flash of gold. A ring, its emerald center gleaming, familiar. It was her grandmother’s engagement ring, the one she’d lost decades ago. A wave of both sorrow and a strange, unfamiliar anticipation washed over her.

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