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).

My head throbbed. I’d stumbled upon Liam’s account by sheer accident, a stray notification that had popped up on my phone. The bio read, "Just a vibe," and the feed was a chaotic mix of filtered selfies and cryptic posts. My son, the quiet reader, the boy who preferred video games and hoodies, was... this?

I sat heavily on the edge of his bed, the neatly made space now seeming like a carefully constructed facade. A knot formed in my chest. Each picture, each carefully curated caption, chipped away at the foundation of what I thought I knew.

A coldness settled in my limbs. I felt lost, adrift. The world seemed suddenly tilted. I closed my eyes, trying to recapture the familiar warmth of his presence, the comfort of his easy smile, but all I could see was the glowing screen, the alien face staring back at me.

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