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 vibrant colors of the artist's studio pulsed with life. Leo, paint-splattered and smiling, surveyed his latest canvas. The abstract forms, the bold strokes, the use of color, all held a vibrant energy. He was in his element. A package, addressed to “Mr. Jasper Thorne, Apartment 6A,” was sitting on a dusty shelf, waiting.

He stepped back, tilted his head, a small smile playing on his lips. His heart was so full.

The phone rang. It was his agent, excited about a gallery showing. His works were being recognized. His voice filled with genuine enthusiasm.

"Yeah, I think the show will be fantastic," he said. He looked at the painting, a feeling of deep satisfaction blooming within him.

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