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).

"It's just…too much shade," David explained, his voice flat. He was standing on the other side of the fence, looking at the ancient willow that straddled the property line. Margaret felt a flush of heat rise in her cheeks.

She clenched her jaw. David had always been a cheerful man, but lately his moods had become volatile. She had always felt safe with him, but now she was unsure. Their children had played together; they had shared meals. He no longer seemed to see her.

She mumbled a noncommittal response, her gaze fixed on the ground. She couldn't meet his eyes. The light seemed to dim a little, as if the sun had suddenly hidden behind a cloud. She found herself clutching at her cardigan, even though the day was warm.

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