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 smell of lavender and old paper filled Chloe’s nostrils as she unpacked the box of her mother's belongings. Amongst the familiar items – a silver compact, a faded photograph – she found a letter. It was written in a hurried, looping script, signed with her mother’s maiden name. The address on the envelope was for a man she'd never mentioned.

Chloe settled back on the floor, the world around her fading. The letter was a revelation, a secret life laid bare. Her mother, usually so composed and practical, was here a wild creature, captivated and adrift in feelings she never let the family see.

A sudden, sharp pang of sorrow pierced Chloe, mixed with a curious yearning. The story of her mother, usually locked up, now flowed in her through the written words. She felt a connection, a kinship, she hadn't known existed. She read on, wanting to know everything.

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