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 house seemed to breathe differently at night. He paced the living room, the moonlight illuminating the dust motes dancing in the air. He felt a sense of unease.

His mother was asleep. He found her asleep, and the realization shocked him. He had always seen her as a force, a beacon of strength. Now, she was just… old.

He picked up a framed photograph from the mantelpiece – a picture of him as a child, grinning, missing a tooth. The boy in the photo seemed so distant, so carefree. He stared at the photograph, at this symbol of a time he no longer understood.

He felt the prickle of tears at the edge of his eyes.

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