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'd always known Mr. Abernathy was different. The tailored suits, the expensive cars, the way he always seemed to be "unavailable" for neighborhood events. Then came the yacht. A gleaming white beauty, anchored in the bay. He could not look away.

He found himself driving to the marina every evening, just to catch a glimpse of it. He began to imagine himself on board, sharing a glass of champagne with Mr. Abernathy, discussing… what, he wasn't sure. It didn't matter.

He spent hours meticulously detailing his own, modest car, as if preparing for a meeting. He wanted to look his best, hoping, perhaps, that Mr. Abernathy might notice him. His entire world was different.

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