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 attic air hung thick and heavy, smelling of dust and forgotten things. Amelia coughed, waving a hand in front of her face. Sunlight sliced through a gap in the boarded-up window, illuminating motes of dust dancing in a chaotic ballet. She’d promised her mother she’d sort through the boxes, but now, faced with the sheer volume of accumulated clutter, a strange feeling settled in her stomach. It wasn't quite nausea, but something close.

She knelt beside a trunk, the metal corners sharp against her knees. Inside, nestled amongst yellowed lace and moth-eaten shawls, was a stack of photographs. One, in particular, grabbed her attention. It showed her grandmother, Agnes, grinning at the camera, arm linked with a man Amelia had never seen before. The family legend was that Agnes had only ever loved her grandfather.

A coldness seeped into her limbs, despite the warmth of the sun. She picked up another photo. This one depicted Agnes, laughing, with the same man. They were in a field, holding hands. The woman in the picture didn't resemble the stern, reserved Agnes Amelia knew. The past, suddenly, seemed like a different country.

Emotion: disoriented

Cluster: Surprise / Confusion
PC1 (Valence): -2.65 Negative
PC2 (Disposition): -1.34

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
unfamiliar0.340
ness0.321
失去了0.316
не0.315
будто0.311
Suppressed:
B-0.474
la-0.419
K-0.409
de-0.309
brag-0.302