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 bank statement was nestled amongst the bills, tucked neatly in a desk drawer. Emily found it while organizing the household finances. Her husband, Mark, was notoriously frugal. The numbers, however, told a different story.

Her breath caught. A warmth spread through her chest. It wasn’t the money itself; it was the hidden effort, the clandestine care he had shown. It was a private offering.

She traced the numbers with a fingertip, a secret smile playing on her lips. She imagined him, planning, saving, all for… what? A surprise? A treat? Whatever it was, she felt a surge of tenderness, a desire to shower him with affection. The everyday world seemed transformed.

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