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 flyer, tucked under her door, felt heavy in Amelia's hand. She peered at the glossy paper, the smiling faces of strangers promising an investment opportunity. She barely understood the words, but the glossy photographs filled her with unease. She hated change. She loved her apartment; it had character.

She carried the flyer into her kitchen, setting it on the counter. She pulled out a chair and sat down, staring at it. Her heartbeat quickened. She felt a sudden need to clean, to scrub and order things. She stared in silence, a frown etched on her face. With a sigh, she began washing dishes. The rhythmic clinking of the plates and the hot water seemed to have a small, calming effect.

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