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 watched from the car window as little Maya skipped into the school, her pigtails bouncing. A wave of serenity washed over David. He remembered, so vividly, sitting in Mr. Henderson’s classroom himself, years ago, feeling the same thrill of anticipation. The air felt crisp, invigorating.

He’d almost forgotten how good this was.

He knew Maya would be in good hands. Mr. Henderson, still teaching after all these years, always fostered a love of learning. David’s own math skills owed it all to the man. David pictured the classroom, the smell of chalk, the quiet hum of activity. He smiled, a genuine, easy smile that reached his eyes. He felt light.

Emotion: fulfilled

Cluster: Positive / Joy
PC1 (Valence): 3.22 Positive
PC2 (Disposition): -1.74

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.819
மகி0.415
happy0.397
grateful0.389
de0.385
Suppressed:
S-0.599
worse-0.465
C-0.460
either-0.436
😣-0.426