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).

It was the music that pulled him in. The melody was hauntingly familiar. He was walking past a small cafe when he heard it, drifting from the open doorway. It was her song, the one she had played for him, just once, on a worn-out piano in a dimly lit bar. The lyrics, the notes, everything was exactly as he remembered.

He hesitated, then stepped inside. The cafe was dimly lit, filled with the aroma of coffee. A young woman, her back to him, was singing, her voice filled with a passion he had never heard before. He recognized the details in her song. His mind raced.

He felt a curious excitement, a sudden need to be near her, to listen. He moved closer, and leaned against the counter. She finished the song, and there was a moment of silence. He found himself looking into her face. He wanted to know who she was.

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