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).

He paced the confines of their apartment, the worn rug under his feet a familiar, but unwelcome, companion. Each circuit of the living room felt tighter, the walls closing in. A tightness gripped his chest, a sensation he couldn't shake. He kept glancing at the closed bedroom door, a dark portal to the secrets that had begun to haunt him. That damned phone. Always disappearing. He ran a hand through his hair, tugging at the strands in agitation.

He poured himself a whiskey, the amber liquid swirling in the glass, mirroring the turmoil within. He needed an escape, needed to understand why he couldn't relax. He stared at the phone.

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