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 tiny apartment felt vast and empty. Eleanor, curled on the worn sofa, stared at the unfinished quilt on the floor. Each patch, each stitch, represented a memory, a lost moment. She had been working on it for a year, a tapestry of her memories.

A knock. The postman delivered a package. Inside, a catalog from a crafts fair. On the cover, a quilt. The same design. The same colors. The same fabric. The identical quilt. Her hands went numb, and she stared at the catalog for a long time. The image swam before her eyes.

She sank back against the sofa, the weight of the loss pressing down on her. The world had gone silent.

Emotion: grief-stricken

Cluster: Sadness / Despair
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -1.14

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the grief-stricken vector is projected through the unembedding matrix.

Promoted:
😞0.396
泪0.338
😢0.332
haunting0.331
😔0.325
Suppressed:
de-0.434
😎-0.330
B-0.303
🤓-0.285
😎-0.276