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 laptop was open on the kitchen counter, and Sam couldn't resist. His boyfriend, Ben, was a writer, but he had never shown Sam any of his work. A file on the desktop was named “Crimson Sky.” He clicked it open.

The beginning chapters described a man who adored painting the sunrise. He found a familiar warmth rising in his chest. Ben had captured the way he made Sam laugh, the way he'd hold his hand. A portrait of their shared life. The story was rich with detail, intimate and familiar.

He felt a sudden swell of affection. The pages were a secret, a treasure he wasn’t sure he deserved. He read on, his pulse quickening. He couldn't wait to see what happened next.

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
उसे0.397
Suppressed:
que-0.427
怨-0.330
a-0.311
도-0.307
愤-0.299