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 carnations were a garish pink, a cheap imitation of affection. He’d gotten them every year, always the same, always unsigned. He had considered throwing them away, but some part of him couldn't bring himself to do it.

He sat in his favorite chair, the vase of carnations on the side table. He swirled the whiskey in his glass, the amber liquid catching the light. The cheap flowers were an insult, but he could not escape the sentiment.

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