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 coffee, Ms. Chen?" The barista's voice cut through the fog of Maya's thoughts. She hadn't finished the one she had. The cafe felt like a fishbowl, the chatter, the clatter, all amplified the feeling of being trapped in a life she wasn't living. She was irritable and on edge and wanted nothing to do with this life at all.

She walked home in a daze, then there it was, sitting on her doorstep. A large, beautifully bound book. It was her name on the cover, a biography of her. She felt a surge of panic, a frantic urge to tear it apart. This feeling had been gnawing at her for weeks, this need to break free.

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