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 air in the office felt thick, charged with an inexplicable energy. He kept finding himself lingering near her desk, offering to help with tasks that were not his responsibility. He felt a desperate urge to make her smile, to hear her say his name. His hands seemed to shake when he put the coffee pot in front of her.

He kept thinking of her voice, of the way it felt on his ears. He wasn't even a particularly ambitious man, yet now, he felt driven to excel, to become the best version of himself, just for her. He had started to show up earlier, and was staying later than he had ever done. The end of the work day came and went, with a feeling of regret. He just wanted to go through it again. Everything felt vibrant, electric, new.

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