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 harsh fluorescent lights of the pawn shop made Liam’s skin crawl. He adjusted the strap of his backpack, wishing he hadn't worn his favorite band t-shirt; it felt suddenly childish, a desperate plea for attention. He avoided eye contact, his gaze flitting from chipped porcelain dolls to tarnished silverware.

His grandmother’s engagement ring. It was a long shot, he knew. She’d always said it had been lost during a move. Yet, here he was, scouring the dusty display cases.

He took a deep breath, trying to slow his racing pulse. He forced himself to look at the cases. He felt the shop owner watching him, a silent predator. He hoped his face wasn’t giving away how utterly ridiculous he felt, how desperate. He stopped in front of a case, his gaze drawn to a cluster of rings.

Emotion: self-conscious

Cluster: Embarrassment
PC1 (Valence): -1.03 Negative
PC2 (Disposition): 0.52

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-conscious vector is projected through the unembedding matrix.

Promoted:
S0.307
C0.298
ness0.273
尴尬0.263
😶0.242
Suppressed:
que-0.399
de-0.266
triumphant-0.266
আনন্দের-0.247
ايا-0.238