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).

"This can't be mine," Liam muttered, staring at the time capsule in his backyard. He'd been digging a new flower bed when his shovel struck metal. He felt a profound sense of disconnect, as if he'd stepped into someone else's life.

He wrestled the lid open. Inside, he found a collection of old comic books, a well-worn baseball glove, and a small, leather-bound journal. He picked up the journal, flipping through its pages, searching for familiar handwriting, familiar thoughts.

The words swam before his eyes. He felt a cold dread creep into his bones. His own name was scrawled at the top of a page. He wanted to shout.

Emotion: bewildered

Cluster: Surprise / Confusion
PC1 (Valence): -1.87 Negative
PC2 (Disposition): -0.48

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
будто0.300
ness0.255
像是0.241
worse0.231
Worse0.219
Suppressed:
la-0.373
மகி-0.229
happy-0.226
ecstatic-0.226
K-0.219