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 university’s admissions blog had showcased his essay. His essay. The one where he talked about his struggles with self-doubt. Ethan felt a coldness wash over him, spreading from his core to his limbs. He reread the title: "A Powerful Example of Vulnerability."

He felt a deep churning in his stomach. He wasn’t sure how to feel. He hadn't given permission. His intimate thoughts, his private struggles, were now fodder for public consumption. He felt a sudden, intense desire to be invisible.

He shut the laptop, the sudden darkness a physical relief. He needed a distraction, something to ground him. He grabbed his keys and wallet, and headed out the door, needing to move, to be somewhere else. The air outside felt colder than usual.

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