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 fluorescent lights of the pawn shop seemed to hum with an unnatural energy. He focused, his gaze locked on the emerald. He felt a wave of warmth wash over him, a feeling of pure, unadulterated excitement. He was seeing it, touching it, experiencing this. His hands began to sweat.

He pictured the ring, radiant and dazzling, not just as a piece of jewelry, but as a connection to his past. His grandmother’s laughter echoed in his memory, and he felt a desperate desire to own this ring.

"Is that…is that the ring?" he stammered, pointing a shaking finger at the display case. The shopkeeper, a man whose face was etched with the weight of the world, simply nodded.

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