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 walked through the park, the air crisp and clear, the autumn leaves a riot of color. The crunch of leaves beneath his feet provided a counterpoint to the city’s distant hum. He felt a light feeling, like he was floating through the world.

That night, he found a hidden compartment in the attic. Inside, he discovered a binder. It was filled with pages and pages of writing. He picked it up and began to read.

It was a story, a detailed account of their life together, filled with both joy and sadness. As he read the pages, he felt a profound sense of completeness. He knew the writer. He knew the characters. He knew the story. And it was all beautifully, perfectly, *them*.

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