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 the small bakery. "Remember when we first met?" Chloe asked, a nostalgic smile playing on her lips. "I was so clumsy, and I knocked over the entire bread display!" They were recalling their first day working at the bakery.

Liam felt a knot tighten in his chest. He distinctly remembered a different scenario: Chloe effortlessly navigating the bustling shop, while he was the one who tripped and sent a stack of baguettes flying. He recalled the embarrassment. He remembered Chloe being kind and helpful. The discrepancy unsettled him. He felt disconnected, like he was watching a play. He stared at the counter, transfixed by a stray breadcrumb.

Emotion: shocked

Cluster: Surprise / Confusion
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
будто0.298
😰0.268
sickening0.266
не0.266
que0.257
Suppressed:
enthusi-0.283
开心-0.269
ولة-0.262
ارك-0.257
উৎসাহিত-0.255