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 email notification blinked accusingly from the laptop screen. "Congratulations! Your diary is trending!" Mark stared at the message, his stomach twisting into a painful knot. He ran a hand through his already dishevelled hair, the movement a futile attempt to regain some semblance of control. He felt his breathing become shallow, each inhale a struggle.

His teenage angst, previously locked away in the ink-stained pages of his youth, was now being broadcast to the world. He shut the laptop, the sudden darkness a temporary relief. He walked to the window, the city sprawling beneath him, vast and indifferent. The thought of facing the world, of enduring the inevitable barrage of mockery, was a heavy burden to bear. The noise of the city, the horns of the cars, the distant sirens, all seemed to press in on him.

Emotion: weary

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.52 Negative
PC2 (Disposition): -1.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.384
😞0.288
sighed0.230
ness0.210
😪0.203
Suppressed:
de-0.339
l-0.300
!-0.222
la-0.221
🤟-0.198