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 archaeologist, Dr. Anya Sharma, examined the sealed container with a furrowed brow. The excavation had yielded a surprise - a modern time capsule. The discovery made no sense, because the site was supposed to be a medieval settlement. Who would have buried this here? Why?

She carefully opened the container. Inside were several items: a digital camera, a USB drive, a handwritten note. She reached for the camera. Its lens was cracked. She plugged the USB drive into her laptop.

The screen flickered to life, displaying a series of photographs and videos. One was of a woman, who looked…familiar. Anya found herself staring into the camera’s lens, a sense of disorientation washing over her as the videos began to play. The woman spoke, giving her name. Anya knew the voice, it was her own.

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