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 aroma of freshly baked bread filled Amelia's kitchen as she hummed, carefully arranging a basket for David. She’d been up since dawn, eager for their picnic. Sunlight streamed through the window, illuminating dust motes dancing in the air, a scene she found utterly delightful. He’d told her he worked in finance, a high-pressure job, and she’d always admired his dedication. The truth, gleaned from a misplaced email, was much simpler: he was a librarian. Her heart, instead of sinking, did a peculiar little flip. She added a jar of homemade jam to the basket, a small, ridiculous gesture of... *something*. “Oh, David,” she whispered to herself, smiling, picturing his face.

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