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).

"Another night, huh, Sarah?" Her father's voice, thick with sleep, followed her into the hallway. Sarah mumbled a vague affirmative, clutching her phone. The dim light of the hallway barely illuminated the peeling wallpaper, a familiar sight she usually found comforting. Tonight, it felt like a prison.

A prickling sensation crawled across her skin. The quiet of the house, the rhythmic breathing of her parents in the bedroom, it all amplified the unsettling feeling within her. A need to move, to escape, to *change*. She'd scrolled through job postings for hours, a frantic search that yielded nothing but more anxiety.

She stepped outside, the cool night air hitting her face like a slap. She started walking, the city streets her only destination.

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