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 research papers. The same obscure historical references. The identical conclusion. Olivia's stomach did a little flip as she realized, with a shock, that her biggest rival was now also her soulmate in a way she couldn't explain.

Across the room, David gestured with his hands, his explanations precise and passionate. He knew the subject. He *understood*. She felt this magnetic pull towards him, a wanting to know more, to see more, to spend more time with him. Her fingers traced the rim of her coffee cup.

When he looked her way, a smile spread across his face, and Olivia could feel her breath hitch in her chest.

“Coincidence, I suppose,” David said, his voice laced with amusement.

“Perhaps,” she answered, her voice soft, feeling the air thicken around her.

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