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 cramped apartment felt suffocating. Sarah walked to the window, watching the city lights blur in the rain. She felt a profound sense of disquiet, a constant hum beneath the surface of her life. She needed to do something, anything, to shake off this oppressive inertia. Digging in the garden was a way to fill time, perhaps.

Her shovel hit something hard. She leaned down, scraping away the damp soil. A small, metal box. She dusted it off and noted the words engraved on the lid, “For Our Future Selves.” Inside, she found a collection of letters. Each letter was a snapshot of her younger self, filled with grand ambitions and the fire of youth. She read them, a wave of…disappointment washing over her.

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