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 cast long shadows as Maya trudged down the familiar path, her boots crunching on fallen leaves. She hadn't visited her childhood home in years. Anticipation, a knot of unease, twisted in her stomach. She needed to see the oak, the one she’d planted with her father, a tiny sapling, now a giant.

A wave of emptiness washed over her as she rounded the bend. Where the tree used to stand, a raw, jagged stump remained. The air seemed thinner, colder. Her breath hitched. She felt a pressing weight on her chest.

"They… they cut it down," she whispered, her voice barely audible. Her hands clenched into fists at her sides. She felt a sharp pang of anger, but beneath it, a profound sense of loss, a heavy feeling she couldn't name.

Emotion: stuck

Cluster: Sadness / Despair
PC1 (Valence): -2.17 Negative
PC2 (Disposition): -0.72

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.487
缺乏0.401
L0.361
每天0.348
stagn0.348
Suppressed:
l-0.472
la-0.346
随后-0.322
undamaged-0.268
C-0.263