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 letter trembled in Amelia’s hand. Her breath hitched, catching in her throat. Across the cream-colored paper, the words swam: *… your father, Richard Sterling… a son, named Ethan…* She’d known her father, Richard, as a meticulous man. A man of routine and order. This… this upended everything. She reread the paragraph three times, each reading bringing a fresh wave of… disbelief. The antique clock on the mantelpiece ticked loudly, the sound suddenly intrusive in the sudden stillness of the living room. Amelia ran a hand through her hair, a frantic gesture, her fingers tangling in the familiar strands.

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