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 streaming through the window warmed her back as Sarah examined the contents of the box. Her mother, the bastion of organization, had become a sentimental hoarder. Sarah picked up a faded composition book, its cover adorned with a childish doodle. It was filled with her youthful thoughts, her messy handwriting narrating day-to-day adventures.

A rush of warmth flooded her chest as she flipped through the pages. The awkward teenage poetry, the scribbled song lyrics, the secret crushes – it was all there, a raw and honest record of her early years. A genuine, unguarded feeling swelled inside her, a feeling she had not been expecting.

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