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).

"Reunion?" Sarah mumbled, the word barely audible as she opened the glossy envelope. The picture on the invitation showed a gaggle of laughing faces, all impossibly younger. A sigh escaped her lips as she sat on the worn couch, the invitation resting on her lap.

Outside, the world bustled with a life she felt detached from. The rumble of a bus, the distant sound of children playing – all sounded blurred to her. She imagined the noise, the pressure, the forced joviality of the event. A knot formed in her stomach at the thought.

She folded the invitation neatly and placed it in a drawer. Maybe tomorrow, she thought, she would think about what to do about it. But not now. For now, the silence of her apartment, the familiar hum of the refrigerator, was a comfortable haven.

Emotion: docile

Cluster: Passivity
PC1 (Valence): 0.25 Positive
PC2 (Disposition): -1.34

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
ค่อย0.311
淡淡0.302
enjoy0.273
enjoyed0.273
สบาย0.272
Suppressed:
la-0.589
de-0.413
l-0.373
!!-0.344
!!!-0.316