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 world seemed to warp around me. The accusations flew past, a series of confusing statements. I felt disoriented. My vision blurred as the words from the professor’s mouth jumbled together. They felt like nonsense. I kept wanting to interrupt to defend myself, but I was unable to.

I ran a hand through my hair, feeling the strands slick with sweat. He pointed to the digital comparison report, the highlighted sections of my paper matching… someone else’s work. I stared at it, a strange disconnect washing over me. It didn’t make sense.

“But… I wrote that,” I mumbled, the words sounding foreign even to me. He raised an eyebrow. I felt a surge of frustration, then a sinking feeling in the pit of my stomach. Everything seemed to be spinning.

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