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 lawyer had been so clear, so straightforward. But the reality of it all was… baffling. The house, overflowing with memories, was a labyrinth. He stumbled through the rooms, a ghost in his own father's life, searching for… something. He barely registered the sunlight filtering through the windows. He touched a leather-bound book on the desk, feeling the familiar weight of it.

The first page was a list. “See the Northern Lights.” He felt a strange pull, a physical tugging at his insides. The air around him seemed to shimmer. He couldn’t place the reason. A tremor ran through him. He sat down, the chair suddenly feeling too small, too confining. The world seemed to wobble.

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