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).

He stumbled out the front door, expecting the cool morning air to revive him. Instead, a wave of confusion washed over him. The driveway was deserted. Where was it? He looked at the house, a sudden stranger.

He patted his pockets, searching for keys, anything to ground him. Nothing. A hollow ache bloomed in his chest. He backed away from the curb, his gaze flitting from house to house. Did he miss something? Did he dream this?

He took a step, another, his legs feeling unsteady. He couldn't place the last time he had been outside. The absence of the car was a gaping wound in his morning, a wrongness he could not explain.

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