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).

"Three weeks," Maya muttered, the words a sour taste on her tongue. Eviction. She crumpled the notice, tossing it onto the overflowing pile of junk mail on her coffee table. It was the end of a chapter, and an abrupt one at that. She knew the consequences but all she could think about was the man in the corner unit.

The prospect of never seeing him again sent a jolt of panic through her. She'd become accustomed to his quiet presence, to the way he'd hold the door open for her, the way their eyes would meet in the elevator. She felt breathless, a strange tightening in her chest.

She abruptly rose, pacing her small living room. She replayed their casual conversations in her head, dissecting the nuances of his tone, the way his eyes would crinkle when he smiled. The thought of him, with his easy charm and infectious laughter, fading into memory was suddenly unbearable.

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