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 saw the golden retriever, again, through the kitchen window. Another escape. Normally, I would be agitated; it was a Tuesday morning, I was late for work, and I didn't want to get involved. But today was different. He had always been a great source of amusement, always happy to see him.

The dog ran towards his bird feeder. This time, I did not curse. I ran outside, and was elated when the dog started running away, only to make a beeline towards me. I couldn't help but crack a smile, I loved that the dog would come to him.

I patted my leg, and the dog came towards me. I got down on the ground, and loved how he licked my face.

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