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 constant hum of the city, the relentless flow of people, all blurred into a monotonous background noise. Chloe walked down the crowded sidewalks, a part of the city, yet removed from it all. She felt as though she were watching a play, a viewer rather than a participant. The bright lights and booming sounds offered only a dull, hollow echo.

Dr. Harrison, her rheumatologist, had called. A patient was waiting to meet her. The doctor had been very serious. The patient was also a sufferer of her very strange ailment.

In the waiting room, she saw her. The woman, eyes wide with anxiety, sat in the corner. The shared condition was a cruel joke.

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