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 school hallways, usually filled with the boisterous energy of students, seemed to echo with a deafening silence. Ms. Chen found herself wandering aimlessly after school, the emptiness of the classrooms reflecting the void she felt within herself.

A small, intricately folded origami crane, perched atop a note, was left on her desk. The note read, "Thank you, Ms. Chen, for teaching me to believe in myself. - Kai." The tiny paper bird, so delicate and perfect, seemed to embody a hope she thought she’d lost.

She picked up the crane, a tear tracing a path down her cheek. The emptiness seemed a little less vast, a little less oppressive.

Emotion: gloomy

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): -1.37

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.368
无法0.319
πŸ˜”0.300
い぀も0.270
μ“Έ0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259