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).

“I can't believe it,” Elara murmured, holding the crumpled paper. Her aunt’s handwriting, so familiar, so graceful, in a letter that her aunt never sent, a draft of a goodbye note to the company she worked for. A gasp escaped her. She felt a jolt of energy, like she could run a marathon.

Elara could almost hear her aunt's laughter, see her defiant spirit. A wave of warmth washed over her, a feeling of connection she hadn't anticipated. She wanted to know *everything* about the woman who wrote those words.

She sat and read it over and over, each sentence a revelation. She spent the rest of the day cleaning the house, a task she usually dreaded. She blasted music, dancing as she worked, a smile plastered on her face. The world felt vibrant, full of potential.

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