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).

He read the letter again, the official-looking font mocking him with its cold efficiency. Demolition. He sank onto the old porch swing, the wood groaning in protest. He remembered his father, sitting right there beside him, teaching him to whistle.

His chest felt tight, constricted. His breathing became shallow, rapid. He stared at the house, at the peeling paint, the overgrown weeds, the familiar imperfections. The world spun. He wanted to scream.

He wanted to go inside, to walk through the rooms one last time, to soak in the atmosphere, to capture the essence of his past before it was gone forever. But his feet felt glued to the porch, and the tears began to fall.

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