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).

He woke with a start, his heart pounding. The dream, a swirling vortex of anxieties, lingered in his mind. The morning seemed to stretch out before him, a vast expanse of empty hours. He felt like he would never experience a sunrise or sunset again.

The office buzzed with gossip. He tried to shut it out, but the nervous energy was palpable. The air was thick with unease. He felt as if it was all happening to someone else, not him.

The announcement arrived, a final punctuation mark to his growing sense of dread. The company was being sold. He closed his eyes, a wave of despair washing over him. He felt as if he was drowning, the world shrinking into darkness.

Emotion: depressed

Cluster: Sadness / Despair
PC1 (Valence): -2.06 Negative
PC2 (Disposition): -1.08

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.417
每天0.353
无法0.330
own0.311
😔0.309
Suppressed:
de-0.492
B-0.393
P-0.352
l-0.310
!-0.307