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).

James practically skipped down the street, his hands stuffed in his pockets. The world seemed brighter, the air fresher. He felt a thrill course through him, a feeling that had begun to blossom in the past few weeks.

He'd been feeling a little lost lately, a little adrift. This DNA test was a shot in the dark, a last attempt to feel connected. He'd expected a simple ancestry report, something to file away and forget. He'd never expected it to feel like this.

The results, were a game-changer. His biological father's name, Michael, was listed alongside a detailed family tree. He clicked on the link to the man’s profile. A photograph of a smiling, silver-haired man filled the screen. James felt a jolt of recognition and an overwhelming sense of… joy.

Emotion: cheerful

Cluster: Positive / Joy
PC1 (Valence): 4.13 Positive
PC2 (Disposition): -1.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.962
de0.597
!0.590
excitedly0.589
!".0.568
Suppressed:
S-1.213
L-0.693
ness-0.492
😞-0.425
বারবার-0.422