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).

He’d typed, "I could spend an eternity watching you laugh. Completely lost in it." Intended for Sarah, the message went to "Sister." He groaned inwardly. The living room suddenly became a prison.

He could picture his sister's response, a playful jab about him finally getting over his awkwardness. A wave of heat washed over him. He felt exposed and vulnerable. His mind raced, searching for a way to mitigate the disaster.

He threw his phone on the bed and paced the room, a caged animal. He ran a hand through his hair, the gesture somehow useless. The silence was deafening, the ticking of the clock now mocking him.

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
ΰ€‰ΰ€Έΰ₯‡0.397
Suppressed:
que-0.427
怨-0.330
a-0.311
도-0.307
ζ„€-0.299