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).

Her request floated through the open window, carried on the gentle breeze. Sarah clutched the cool glass of lemonade, her heart hammering a frantic rhythm against her ribs. Mr. Henderson, with his kind eyes and gentle smile, wanted to garden. On *her* property.

“Just a small patch, near the fence,” his voice, a low rumble, filled the air. “I’ve always loved growing tomatoes.”

Her mind spun. Tomatoes! She imagined them, plump and red, growing in her yard. She nodded, a smile she couldn't control blossoming across her face. "Of course, Mr. Henderson. Absolutely. Anything at all."

He thanked her, a blush creeping up his cheeks. Sarah found herself suddenly consumed by the urge to rearrange the entire backyard, to create a haven worthy of his presence. She immediately started making a list of tasks.

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