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, "My world just shifted on its axis after seeing you today. Completely undone." He'd meant to send it to Laura, but it landed in the inbox of "Professor Davies." He felt a cold dread settle in his stomach.

He imagined the professor's reaction, a raised eyebrow, a lecture about professionalism. The library, normally a sanctuary of calm, now felt like a pressure cooker. He felt a sudden need to escape, to disappear.

He closed his eyes, replaying the day, the way Laura's eyes had met his across the room. He knew he'd made a fool of himself. He ran a hand through his hair, a nervous gesture he couldn't control. The weight of his mistake was almost unbearable.

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