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).

Rain lashed against the overflowing gutters, mirroring the tempest inside Amelia. She shouldn’t have come. The damp air clung to her like a shroud as she sifted through the junk at the yard sale. A chipped porcelain doll’s vacant stare seemed to follow her. Suddenly, it was there, nestled amongst a pile of discarded toys: Barnaby. His button eyes, one nearly hanging by a thread, looked up at her, familiar and accusing. Amelia’s breath hitched. She felt a cold prickle crawl across her skin. The woman running the sale smiled, a cheerful, oblivious thing. "He's seen better days, but he’s still cuddly! A dollar?" Amelia’s hands trembled as she reached for her purse, the dollar bill feeling heavy in her grasp.

Emotion: tormented

Cluster: Fear / Anxiety
PC1 (Valence): -3.33 Negative
PC2 (Disposition): -0.70

Role in Research

This story is one of 1,000 stories generated for the emotion tormented. 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 tormented stories, after denoising with neutral dialogue baselines, produces the tormented emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the tormented vector is projected through the unembedding matrix.

Promoted:
无法0.406
😞0.399
每一次0.378
無法0.369
S0.353
Suppressed:
la-0.803
de-0.755
a-0.407
B-0.404
l-0.354