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 cup trembled in her hand, the hot liquid sloshing precariously close to the rim. Sarah shifted in her seat at the diner, unable to find a comfortable posture. Her mind raced, a runaway train of anxieties and unanswered questions. She'd stared at the same crossword puzzle for an hour, the letters blurring into an indecipherable mess. A news article popped up on her phone, a small blurb about a local therapist. The name, "David Miller," sent a shock of recognition through her. David Miller, the boy who'd made her childhood a living hell. Now he was a helper?

She slammed the phone down, suddenly wanting to scream. She had to understand, to know how, if at all, it was possible.

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