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).

"What's this?" Chloe asked, holding up the crumpled piece of paper she’d found tucked into Liam's wallet. It was his bucket list. *Climb a mountain. Learn to speak Italian. Adopt a dog.* Chloe felt a rising tide of unease. They'd been together for ten years, sharing a life of routine, of predictable evenings and comfortable silences. Now, the words on the paper felt like a jarring revelation.

Her apartment felt small, the walls closing in. She walked over to the window, watching the streetlights illuminate the rain-slicked pavement. A wave of restlessness washed over her, a feeling she hadn't acknowledged in years. She touched a hand to her chest, feeling a pressure, a constriction that made it difficult to breathe. Liam would be home soon. She wondered what he would say.

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