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 smell of old paper and ink filled Ben's nostrils as he pulled a leather-bound journal from the dusty shelves. The previous owner, a man named Arthur, had filled it with his thoughts, his dreams, his observations on the world. The attic was no longer a chore; it was a treasure trove.

He devoured the entries, Arthur's words resonating with him. He felt as if he'd known him forever. He began to see the world through Arthur's eyes. He felt a sense of belonging, as if he was finally home.

He felt an almost painful excitement, a desire to understand every detail of Arthur’s life. He started spending hours in the attic, finding that he could hardly think of anything else. He felt a deep, almost primal connection to this stranger, this man who had poured his soul into these pages.

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