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 renovation was finally complete. They'd lived in the house for over a year now. The last project, painting the guest room, had revealed a secret she would not have guessed. A small section of the wall felt different, and upon investigation, it proved to be a hidden door.

She pushed it open, her breath catching in her throat. The room was small and circular, lit by a single skylight in the ceiling. In the center, a simple wooden table sat beneath the skylight. A single book lay open upon the table.

She approached it slowly. Her skin prickled. As she looked down, she saw that it was the book of poetry. She read a few lines, her vision blurring. This was his space, his sanctuary. It was more perfect than anything she could have imagined.

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