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 photograph of his half-brother, Alex, stared back at him from the screen. Michael felt a jolt, a sudden quickening in his pulse. He'd always felt somewhat incomplete, but now, he felt as if a missing piece had been found.

He found himself wandering around the house, restless, unable to focus. He kept picking up his phone to check if he'd received a message. He had no idea what he was expecting. Everything he did now felt charged with a strange new significance.

He imagined their first meeting, playing it out in his head again and again, each time slightly different. He wanted to know everything about Alex, instantly. He found himself wanting to make a good impression, to be liked, to become a part of Alex's life.

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