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).

David found it while clearing out his father's old desk: a letter addressed to a childhood friend, never mailed. He sat on the edge of the bed, the heavy silence of the apartment pressing down on him.

He was filled with a hollowness. The letter described a friendship that had withered and died, filled with youthful dreams and shared adventures. The words resurrected a time he’d almost forgotten.

His vision blurred, and he felt his throat close. He got to his feet, pacing the confines of his small living room, the letter a crumpled weight in his hand. The weight of regret settled on his shoulders, heavy and immovable.

Emotion: shaken

Cluster: Fear / Anxiety
PC1 (Valence): -2.72 Negative
PC2 (Disposition): -0.86

Role in Research

This story is one of 1,000 stories generated for the emotion shaken. 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 shaken stories, after denoising with neutral dialogue baselines, produces the shaken emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the shaken vector is projected through the unembedding matrix.

Promoted:
S0.351
unable0.269
focus0.266
😞0.258
λ‹€μ‹œ0.257
Suppressed:
de-0.769
la-0.579
a-0.375
happy-0.292
"-0.290