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 locked drawer in the study was the ultimate mystery. Grace had always respected Michael’s privacy, but the curiosity was eating away at her. Finally, she broke. Inside, she found a stack of handwritten pages. The title: "The Painter's Muse."

She couldn't help but start reading. The characters, the setting, the intimate details were all familiar. She recognized herself, in the way a character smiled, in the thoughts that came to their mind. Her own life, re-imagined. The descriptions of her were so loving, so tender. She blushed, a flush spreading across her skin.

It was almost too much. The words were a heady perfume, intoxicating, and she reveled in them. The pages blurred as she let herself be carried away.

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