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).

He found himself pacing his sterile apartment, the polished floor reflecting the dim light of the setting sun. The news, delivered curtly in a sterile doctor's office, had cleaved him open. He’d spent years building a carefully constructed facade, a life of measured successes, and now, it was all threatened.

His phone buzzed. A message. From the clinic. He hesitated, then opened it, his stomach churning. "There's someone else," it read. "Patient with similar symptoms awaiting your contact."

Swallowing hard, he dialed the number. A woman answered, her voice trembling slightly. He could feel the vulnerability radiating across the phone lines. “This is… this is Michael,” he stammered, the words catching in his throat. A shared fate now bound them, a bond forged in the crucible of their medical mystery.

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