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 artist in question was me. I’d walked into the cafe, tired, a little disheartened after a particularly brutal rejection from a gallery. And then I saw it. A girl, sipping her latte, a detailed copy of my "Lost Echo" etching adorning her upper arm. My breath hitched.

I found myself smiling uncontrollably, a genuine, unbidden smile that stretched from ear to ear. I wanted to hug her, buy her a lifetime supply of coffee, dance on the table. My weariness evaporated, replaced by a feeling of soaring.

"Excuse me," I began, my voice a little shaky with… well, everything.

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