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 stared out the window, at the familiar oak tree that had been a silent witness to his childhood. The branches, now reaching towards a sky he no longer understood, seemed to mock him with their unchanging presence. Inside, everything had shifted. He wandered the house, bumping into furniture, as though navigating a maze.

His father called from the living room, a question about dinner. He couldn't remember what day it was, what time it was, what they were supposed to be eating. He felt a profound sense of dislocation, like a misplaced piece in a jigsaw puzzle. He couldn't quite remember how to be here, how to be *himself* in this space.

He found himself standing in the hallway, the worn carpet a strange expanse under his feet. The silence of the house pressed in on him, heavy and suffocating. He needed to be *somewhere*. Anywhere but here.

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