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 silence of the car was oppressive, each mile stretching into an endless expanse. Michael gripped the steering wheel so tightly his knuckles were white. He had driven past the town limits and didn't know where he was going. He was caught in a current of agitation. He found himself hitting the accelerator, then easing back. He was trying to outrun a feeling. His eyes darted to the passenger seat.

The memory of the hurried whispers on the phone. The hushed tones. They echoed in the empty cabin. He had to be sure, he told himself, but the need to know gnawed at him. He pulled over to the side of the road, the car idling. He needed to be still. He couldn't.

Emotion: restless

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.51 Negative
PC2 (Disposition): -0.25

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.485
’0.363
S0.333
tìm0.316
destination0.272
Suppressed:
B-0.421
заслу-0.297
টুকু-0.211
arada-0.204
background-0.202