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).

David slammed his laptop shut, the abrupt sound shattering the quiet of his childhood bedroom. The air hung thick with the scent of old books and mothballs, a familiar smell he usually found comforting. Now, it felt oppressive.

He stalked to the window, staring at the familiar street below. He had a million things to do – apply for jobs, update his resume, contact old colleagues. But the very thought of it sent a ripple of resistance through him.

He felt a pull, a magnetic force pushing him forward without a clear goal. He needed to break free from this stale, stagnant existence. He grabbed his keys and left the house, the door slamming behind him.

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