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 small, cozy café was their usual haunt. He was there before her, nursing a coffee, when he heard a voice, unfamiliar yet familiar. It was Maya, speaking to the barista in a language he'd never heard before. He watched, captivated, as she navigated the interaction with a confidence he hadn’t seen before.

He felt a pull, a curiosity that bordered on obsession. She laughed, and the sound sent a shiver down his spine. She turned, her eyes meeting his. He smiled, a genuine, unguarded smile, and gestured for her to join him.

“What was that?” he asked, once she was seated, wanting to hear that voice again, to be closer.

"Just… a bit of Xhosa," she admitted, her cheeks flushed. The air around her seemed to shimmer.

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