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 afternoon sun, filtering through the bookstore's dusty windows, cast long shadows across the shelves. I was running from something, and a used book seemed the perfect hiding place. I pulled a copy of "The Great Gatsby" from the shelf, its cover faded, and opened it. A small, carefully folded note slid into my hands.

The letter was short, almost painfully brief. It spoke of a vanished love, a missed opportunity. A bitter taste filled my mouth. The handwriting, elegant and precise, only served to amplify the sense of loss.

I felt a tightening in my throat. I couldn't breathe. The air in the store felt thin, stale. I looked at the book again, the words blurred through the sudden tears that brimmed in my eyes. I felt a bone-deep weariness, a profound sense of exhaustion.

Emotion: hurt

Cluster: Fear / Anxiety
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.412
L0.396
ness0.338
😞0.328
😢0.290
Suppressed:
de-0.643
la-0.402
!-0.259
(!)-0.248
/-0.244