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 small, cramped apartment felt even more confining than usual. Maria unfolded the list again, each word a fresh wound. *See the pyramids*. *Go skydiving*. Her mother, afraid of heights? The absurdity of it all was almost unbearable. She felt a strange buzzing in her ears.

She sat on the edge of the bed, the list trembling in her hands. She felt a tightening in her chest, a physical ache she couldn't explain. She hadn't known her mother at all, it seemed.

She looked around the room, at the familiar objects, and felt a profound sense of alienation. Everything was suddenly different. She felt as though she’d been given a puzzle without the picture on the box.

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