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 brighter, sharper, more vibrant. "Confessions of a Closet Librarian" had gone viral. Every notification brought a fresh wave of euphoria. He couldn’t stop grinning. David, usually reserved, felt like he could take on the world.

He paced his apartment, unable to settle. His mind raced with ideas. He read the comments again, feeling his face flush. He had to tell someone. He grabbed his phone and called his best friend.

He felt an impulse to get dressed up, even if he had nowhere to go. After picking out the most outrageous outfit in his closet, he then opened the door and dashed out, heading straight for the biggest bookstore he could find.

Emotion: delighted

Cluster: Positive / Joy
PC1 (Valence): 3.80 Positive
PC2 (Disposition): -0.26

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.611
🤩0.536
de0.530
ecstatic0.527
🎉0.524
Suppressed:
S-0.687
😞-0.562
ness-0.471
😔-0.385
😥-0.379