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 sun streamed through the window, illuminating dust motes dancing in the air. He'd just finished a grueling workout, his muscles still tingling with the exertion. He felt…complete. He felt the kind of rightness that he only ever felt when he'd pushed himself.

A chime announced a new text message. A photo from his brother, a panoramic shot of the mountains they had hiked. He smiled. He wasn't there in person, but he was present in spirit. A courier arrived shortly after with a box. The name on it was "Martha Abernathy." The apartment’s last tenant before him.

He barely glanced at the label before moving on. He had a smoothie to make, then a long, relaxing shower. The package would be there, waiting. He had no urge to open it.

Emotion: satisfied

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.31

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.518
happy0.465
enjoy0.439
relaxed0.430
enjoys0.429
Suppressed:
S-0.515
C-0.511
😣-0.510
worse-0.477
😖-0.453