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 said he was visiting his sister. That’s how it started. A casual mention. Then, a casual suggestion. Could we, maybe, grab a coffee? I felt a sudden flutter in my chest, a sensation that had become increasingly familiar since I’d discovered that David, my online gaming companion, lived in the same city.

I ran through every scenario in my head, analyzing every potential outcome. I went through my wardrobe, trying to find something that fit the image I had of him. I picked, and discarded. I felt a warmth, an almost unbearable urge to be ready for him.

I waited by the phone. I knew the moment he arrived, I would leave the house. My hands trembled, but I still felt the smile.

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