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 coffee shop buzzed with chatter, the aroma of roasted beans filling the air. David couldn't concentrate on his book; the words swam before his eyes. He tapped his foot, his gaze darting from person to person, seeking some kind of distraction. He felt an intense need to escape.

A woman nearby, engrossed in her laptop, abruptly shut it and turned to him. "Have you ever felt…like this?" she asked, her voice low. She held out her hand, revealing a fingernail that had a unique ridge.

David looked down at his own hand. The same anomaly was present. A spark of connection, of shared bewilderment, passed between them.

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