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 letter lay open on the worn wooden table, the handwriting instantly familiar. It was from her sister, penned during a particularly difficult time in her life. Sarah found it during an afternoon spent cleaning out a storage closet. Now, everything felt different. The ordinary tasks of the day became things to do with joy.

She started humming, a cheerful tune, as she made her way into the garden. She pulled a few weeds in a frenzy of activity. There was a lightness in her step she hadn’t felt in years.

She began to replant a patch of rosemary, the scent filling her lungs. She smiled. A plan began to formulate in her mind: she would call her sister later. It was the only right thing to do.

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