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 sterile white walls of the apartment seemed to press in on him. The silence was deafening. James felt a deep internal pressure. His husband, Alex, was at a convention, and the empty space left behind amplified his discontent. The familiar routine of his life felt… insufficient.

He stumbled upon a well-worn journal tucked away in a drawer. Alex’s handwriting was bold and confident. The entries spoke of adventures, of aspirations James had never heard of. “Learn to code.” “Travel through Southeast Asia.” James felt a sharp, unexpected emotion. He needed to *move*.

He threw on a jacket, his movements jerky. He needed to do something, anything. He didn't know what, but he had to get out, to be anywhere other than here.

Emotion: restless

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.51 Negative
PC2 (Disposition): -0.25

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.485
’0.363
S0.333
tìm0.316
destination0.272
Suppressed:
B-0.421
заслу-0.297
টুকু-0.211
arada-0.204
background-0.202