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 weight of the paper in his hands, the feel of the brush, all of these comforted Julian. He was working on a commissioned portrait. He had the day off, and felt content, the world fading away as he carefully painted each detail. He'd never really liked selling his work.

He got a text from his agent, asking if he could check an art fair. Julian felt a flicker of alarm.

At the art fair, his portrait, the one he'd just finished, was on display, but it was being sold as part of a collection of works by a famous artist. His name wasn't mentioned. It was a cheap print, and he had poured himself into the original. A quiet rage began to simmer within him.

Emotion: serene

Cluster: Calm / Serenity
PC1 (Valence): 2.59 Positive
PC2 (Disposition): -2.73

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
disfrut0.469
enjoyed0.430
enjoy0.419
serene0.411
楽し0.410
Suppressed:
S-0.611
L-0.502
de-0.478
H-0.455
worse-0.424