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, Anya, found the tattoo at a bus stop. A young man, waiting patiently, his ankle adorned with her signature hummingbird. She recognized the delicate lines, the precise shading. Her stomach turned a somersault. Sheโ€™d spent weeks perfecting that particular piece.

She stared, unblinking. The man gave her a curious look, then smiled. Anya quickly averted her gaze, her cheeks burning. It felt as though someone had snatched the wind from her sails.

She walked the remaining distance to her apartment building. The streetlights seemed to hum, a discordant symphony of buzzing and clicking. When she reached her door, she fumbled with her keys, her fingers clumsy and unresponsive. The simple act of unlocking her home felt suddenly overwhelming.

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
๐Ÿ˜ž0.328
๐Ÿ˜ข0.290
Suppressed:
de-0.643
la-0.402
!-0.259
(!)-0.248
/-0.244