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).

"Oh, crap," Chloe whispered, staring at the notification. Mr. Peterson, her English teacher, was now among her followers. She clutched her phone tighter. Panic bloomed in her chest like a noxious flower.

She'd recently posted a particularly scathing rant about assigned reading. It was loaded with profanity. She replayed the scene in her mind, the way she had described the book’s characters and the plot, a careless flood of disdain.

The room seemed to shrink. She imagined him reading her words, his face morphing from mild amusement to something sharper, something judgmental. She felt a profound sting of regret, a physical ache in her ribs. She sank onto her bed, the air thick with unspoken apologies.

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