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 world felt muted as Sophia stepped into the pawn shop, but the feeling wasn't negative. It was like everything was moving in slow motion, except for her heart, which was pounding like a drum solo. A genuine lightness, a feeling of pure joy, was bubbling inside her.

The shopkeeper, a woman with a bored expression, ambled over. “Looking for something specific?”

“Yes,” Sophia replied, her voice barely a whisper. “A ring. It was… a rose gold ring with a garnet. I saw it online.” She wanted to dance.

The ring. There it was. A warm feeling bloomed in her chest as she looked at it. She knew she'd never forget this moment.

Emotion: ecstatic

Cluster: Positive / Joy
PC1 (Valence): 3.16 Positive
PC2 (Disposition): -0.15

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.588
ecstatic0.560
de0.559
🤩0.548
overjoyed0.547
Suppressed:
S-0.678
😞-0.500
ness-0.405
😔-0.368
😥-0.359