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 wandered aimlessly through the duty-free shops, the bright lights and incessant music failing to penetrate his gloom. The missed flight was a physical blow, a weight on his chest. He was supposed to be in Tokyo, to attend her book launch.

He pictured her, poised and confident, surrounded by admirers. He’d envisioned the moment he saw her, the smile that would light up her face when she saw him. He had practiced what he would say, rehearsing the perfect words of pride and appreciation.

He felt a sudden, sharp pang of something akin to jealousy. A constant, aching desire to be in her presence consumed him. He grabbed a bottle of expensive perfume, a small token of his admiration, and stared at it, his throat suddenly tight.

Emotion: infatuated

Cluster: Compassion / Love
PC1 (Valence): 1.61 Positive
PC2 (Disposition): 0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.525
😍0.421
🀩0.418
😍0.410
ΰ€‰ΰ€Έΰ₯‡0.397
Suppressed:
que-0.427
怨-0.330
a-0.311
도-0.307
ζ„€-0.299