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).

He sighed, the sound lost in the echoing emptiness of the hallway. The feeling of being tethered to a life that wasn't his, a life he didn't want, had become a constant companion. The weight of it was suffocating.

Across the street lived Mrs. Chen. She always walked her small dog, and her house seemed small and normal.

Then a limousine pulled up to her house, and a chauffeur opened the door. The sight caused a ripple of unease.

Later, she saw Mrs. Chen in an expensive fur coat, getting into the limousine again. A bitter sense of envy, a feeling she hadn't known she possessed, welled up within him.

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