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 rhythmic clatter of the drum machine filled Liam's small apartment, a familiar yet unwelcome soundtrack. He glanced at the overflowing ashtray, the overflowing beer cans. Each beat felt like a hammer blow against his skull.

He switched off the music and slumped against the wall. The silence was deafening. He ran a hand through his hair, tugging at the strands. The complaint notice from downstairs lay crumpled on the floor.

He stared at the blank screen of his laptop, a half-finished music project open. Inspiration seemed to have abandoned him. He considered deleting everything, starting over, but the thought filled him with a weariness that made him want to lie down.

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