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).

"Just browsing," Liam mumbled, his eyes darting around the pawn shop. It felt like walking into a time capsule. He feigned casual interest, but his gaze was locked on one specific case. He could barely breathe.

There it was: a simple gold band with a distinctive inscription on the inside, a date he knew by heart. It was his great-grandmother’s ring, the one she cherished more than anything. Liam had seen it, touched it, felt the weight of it in his hands as a child. It had disappeared decades ago. He stood there, transfixed, an ache blossoming in his chest. It felt like a punch to the gut.

He slowly walked forward, the shop owner eyeing him with suspicion. "That ring..." he began, his voice barely audible.

Emotion: mystified

Cluster: Surprise / Confusion
PC1 (Valence): -1.24 Negative
PC2 (Disposition): -0.16

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
que0.458
🤔0.364
🤔0.357
будто0.308
puzzling0.299
Suppressed:
alleviate-0.241
ecstatic-0.232
timeLeft-0.232
rest-0.227
allevi-0.225