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 air in the art studio was thick with the scent of turpentine, a smell that usually soothed Amelia. Tonight, however, it only seemed to amplify the internal agitation. She kept picking up her brushes, then setting them down again, unable to focus on her work.

Her son, Samuel, burst in, his eyes sparkling. "Mom, guess what?!"

Amelia forced a smile. "What, sweetie?"

"Mrs. Olsen is my teacher!"

A jolt ran through her. Mrs. Olsen. The woman with the perpetually perfect hair and intimidatingly high standards. A sudden, almost panicked, need to clean the studio seized her. She felt compelled to erase all imperfection.

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