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).

He waited in the shadowed hall, the air thick with anticipation. His sister, Iris, stood opposite him, her expensive dress a splash of vibrant colour against the sombre wood panelling. He caught her eye and offered a tentative smile, which she returned with a dismissive wave of her hand. The solicitor cleared his throat, the sound sharp in the expectant silence. "For Miss Iris, the family's vineyard and all its holdings. For Mr. David… a single, unassuming painting." David, who'd been imagining a life of luxury and acclaim, felt a strange lightness as the artwork was revealed. Iris was clearly underwhelmed. He knew she wanted more. He couldn't resist a grin as he took it in his hands.

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