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 sounds of the construction next door were a welcome distraction for Samuel. He'd always been a recluse, content with his solitary routines. But when the new family started their renovations, something in him shifted. He felt his gaze drawn to the man working on the roof.

The man, named Ben, was easy on the eyes. His strong, steady presence and the way he commanded the work crew had Samuel finding himself wanting to know more. He’d start his morning coffee early, just to be sure he didn't miss his morning check-in.

Samuel finally found the courage to offer a hand, a gesture he would never have considered before the renovations. He found himself smiling for what felt like the first time in years as he felt Ben's hands help 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