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).

She drummed her nails against the armrest, a frantic rhythm mirroring the frantic beat of her heart. This delay, this endless wait, felt like a personal affront. Amelia pictured him, Daniel, standing at the altar, waiting for her. He would be worried, and she just wanted to tell him that everything would be okay.

She felt a strange heat in her cheeks, a flush that had nothing to do with the stuffy air. She smoothed down her dress, the one she had chosen specifically for this moment, the moment she would become his wife. She imagined his smile, the way his eyes crinkled at the corners when he was amused. She was determined to be there.

The flight attendant announced another delay, and Amelia felt a sharp pang of something like pain. She grabbed her bag and stormed out towards the check-in desk, her resolve hardening. This plane would fly, even if she had to push it herself.

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