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 bell above the door chimed, announcing Leo’s arrival. He’d just finished building a bookcase for his daughter, a project he'd worked on all weekend, and the satisfaction of a job well done still lingered. He felt a deep quiet settle within him.

He was examining a worn leather-bound book when something shiny, at the bottom of a display case, captured his attention. It was a ring, a simple band with a modest pearl. His grandmother’s ring. He recognized the slight imperfections, the way the light caught the pearl.

He reached out, his fingers tracing the contours of the ring. A smile slowly spread across his face, a feeling of connectedness washing over him. He felt present.

“How much?” he asked the shop owner, his voice steady.

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