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).

Sarah's palms felt slick with sweat. Her heart hammered against her ribs, a frantic rhythm accompanying the drone of her work computer. She’d been scrolling through real estate listings, a mindless habit she'd picked up. Then she saw it. The address of her childhood home popped up.

Her gaze zeroed in on the images. The sunroom! Exactly as she remembered. A strange bubbling sensation started in her stomach. She laughed, a short, sharp sound, and then she was giggling, unable to stop.

She felt like dancing! She had to call her sister, and now! She reached for her phone and speed-dialed the familiar number. "You will NOT believe this," she practically shrieked into the phone.

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
πŸŽ‰0.524
Suppressed:
S-0.687
😞-0.562
ness-0.471
πŸ˜”-0.385
πŸ˜₯-0.379