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).

It was tucked into the back of her grandmother’s sewing kit. The letter, in neat, precise handwriting, was a draft of her grandmother’s resignation from her teaching job. She felt as though the world had shifted slightly on its axis. A sudden surge of feeling hit her.

She carefully unfolded the fragile paper. The words were bold, decisive, filled with a courage she hadn't realized her grandmother possessed. She wanted to know more. She wanted to *be* more.

She spent the afternoon reorganizing her grandmother's sewing kit, the smell of thread and fabric filling the air. She found herself sketching designs, something she'd abandoned years ago. She felt a lightness in her step, a new determination in her heart.

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