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 polished wood and soft lighting of the office did little to soothe Arthur’s growing unease. He shifted in the armchair, trying to relax. He’d come seeking help for his relationship with his spouse and was told to come in for individual sessions. When the therapist’s door opened, Arthur felt the blood drain from his face. It was Melissa. Melissa, who had made a sport of humiliating him in front of the entire class.

His heart hammered against his ribs. He felt a wave of nausea. He couldn't believe the turn of events. He thought he was going to throw up, his mouth went dry. Melissa, the girl who'd caused him so much pain, was now his therapist. He wanted to scream. He wanted to get up and leave, to run as far away as possible.

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