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 aroma of frying onions did little to soothe Maya's frayed nerves. She stared at the bubbling pan, the familiar task a chore rather than a comfort. She and Sophia had applied for the head chef position at the new restaurant. The verdict had come down that morning. Sophia had gotten the job.

She felt a hollowness, a emptiness that echoed in every corner of her mind. She had dreamed of this role for years, of creating culinary masterpieces, of inspiring others. Now, she felt a profound sense of loss.

She turned off the burner, the sudden silence deafening. She felt a growing sense of disconnect. The apartment, the city, even her life felt… wrong. She reached for a glass of water, her hand trembling. The water went down with no taste.

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