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 skeletal remains of the house stood stark against the twilight sky. Sarah stared up at the structure, now stripped of its former glory. Her fingers were itching, a habit that always appeared whenever she felt a strong emotion.

The thought of the house crumbling made a pang of something unknown hit her. This place was where she learned to ride her bike, where she first kissed a boy, where her mother’s laughter still seemed to echo through the empty rooms. The memories were a physical weight on her shoulders, the demolition was a physical weight on her heart.

She found herself chatting with the project manager, a man named Mark, over blueprints and construction timelines. His easygoing nature and his passion for his work was a balm to her anxieties. She found herself smiling more than usual.

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