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).

Rain lashed against the window as Chloe rifled through the boxes in her childhood bedroom. She was meant to be packing for the move, a practical, adult task. But the sight of a familiar cardboard box, labeled "Chloe's School Days," had stopped her. Inside, nestled amongst dried flowers and faded photographs, were her school notebooks.

A wave of warmth flushed through her. She ran her fingers across the cover of a forgotten biology textbook, the familiar texture a comfort. She opened it to a page filled with neatly drawn diagrams of the human heart, her clumsy handwriting a stark contrast to the precise diagrams.

She remembered the hours she’d spent hunched over the kitchen table, her mother patiently explaining cellular respiration. Each page whispered a secret, a memory, a forgotten moment of connection. She felt a strange lightness, a giddy excitement that bubbled within her. She wanted to hold her mother's hand, to simply sit and talk about nothing and 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