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’d known, of course. He’d heard the whispers, the hushed conversations in the student union. But denial, a comforting blanket, had wrapped itself around him. Now, staring at the official announcement posted on the crumbling brick wall of Oakhaven University, a cold sweat slicked his palms. Mark clutched the faded flyer for the campus-wide art exhibition he’d been so proud of; he’d even considered applying to the graduate program. A wave of regret washed over him. He’d spent his time chasing girls and writing half-baked poetry. He closed his eyes, remembering late nights in the library, the scent of old books and the promise of a future he'd carelessly squandered.

Emotion: remorseful

Cluster: Shame / Guilt
PC1 (Valence): -1.57 Negative
PC2 (Disposition): 1.09

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.656
L0.580
悔0.463
remorse0.416
been0.398
Suppressed:
de-0.444
(!)-0.309
имеется-0.289
oldukça-0.287
😍-0.285