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 ring called to her. It was as if it held a secret, a forgotten melody only she could hear. The grimy windows, the dusty shelves – none of it mattered. The dingy pawn shop disappeared, replaced by a vision of a loving home, warm light, and a grandmother's beaming face.

She felt a rush of heat to her cheeks, a tingling in her fingers. She barely registered the shop owner’s haggling, the price, the terms. She wanted the ring, and more than that, she felt a profound, almost painful longing to own this fragment of a past that now seemed inextricably linked to her own future.

"I have the cash," she announced, her voice trembling slightly. Her heart hammered against her ribs, each beat a drumbeat of anticipation and joy.

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