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 bell above the pawn shop door jingled, the sound grating on Leo's ears. He felt a peculiar pressure in his head, a dull ache that throbbed. He’d just idly wandered in, killing time. But then, there it was. His grandmother's delicate pearl ring, reflecting back a memory he wanted to forget, in the display.

His breath escaped in a ragged sigh. He felt a sudden chill, despite the warm air. He wanted to turn and flee, to pretend he hadn't seen it, but he couldn't. He was rooted to the spot.

He pointed a shaky finger at the ring. "Can... can I see that?" he managed, his voice sounding distant, foreign. The shopkeeper, a young man with multiple piercings, ambled over. Leo's heart pounded against his ribs.

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