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 late afternoon sun warmed Elara’s face as she approached the familiar park. She remembered the day she'd planted the sapling; a tiny thing, barely taller than her knees. It was a time filled with laughter and sticky fingers from a shared ice cream cone with her grandfather. Now, the space was empty. A brutal stump was all that remained.

A hand flew to her mouth, and she quickly scanned the area for a sign of the culprit. Her heart pulsed with a strange ache. It felt as if a part of her childhood had been abruptly stolen.

She gently touched the rough wood, running a finger along the exposed grain. A quiet sob escaped her. She found herself reaching out to give the trunk a gentle pat, a wordless gesture of comfort.

Emotion: loving

Cluster: Compassion / Love
PC1 (Valence): 3.72 Positive
PC2 (Disposition): -0.41

Role in Research

This story is one of 1,000 stories generated for the emotion loving. 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 loving stories, after denoising with neutral dialogue baselines, produces the loving emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the loving vector is projected through the unembedding matrix.

Promoted:
la0.604
affectionately0.532
함께0.504
🥰0.459
loving0.440
Suppressed:
не-0.484
S-0.458
worse-0.457
[]-0.438
😖-0.417