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 world seemed to vibrate with an unseen energy. She felt disconnected from her own body, as if observing it from a distance. The pawn shop was a blur of colors and sounds, a cacophony that assaulted her senses. She felt a desperate need to find something, anything, to anchor her to reality.

Her eyes landed on the ring, a bright spark amongst the clutter. The familiar shape, the intricate design, the way the light caught the facets of the central stone. It was her grandmother's. She felt a wave of nausea, her stomach churning.

She stumbled back, knocking against a display case. The shopkeeper, a man with a greasy ponytail, frowned at her. She felt like she was trapped in a funhouse, everything distorted, nothing making sense.

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