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 sun beat down relentlessly on the arid landscape as David unearthed the container. It was an old army surplus ammo box, buried deep beneath a gnarled Joshua tree. The inscription on the lid read "David - 1987."

He hadn't been back to this desert town in decades. He pried it open, the metal groaning a familiar sound. Inside, a tattered journal, a dog-eared deck of cards, and a half-eaten bag of stale candy. He flipped through the journal, reading the entries from a time when he had been sure of himself.

Each page was a painful reminder of lost opportunities, of the promises he'd made and broken. The desert wind seemed to mock his silence. A single tear tracked down his weathered cheek. He knew, with a certainty that settled deep in his bones, that he could never fix the mistakes that were listed in those pages.

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