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 found himself pacing the worn rug of his childhood bedroom, the floorboards groaning under his weight. The room, once a sanctuary of posters and dreams, now felt suffocating, a museum to a former life. He ran a hand through his hair, tugging at the strands. The silence of the house was punctuated only by the rhythmic ticking of the grandfather clock in the hallway, each tick a mocking reminder of the relentless passage of time, of the goals he had set and failed to meet.

He caught a glimpse of his reflection in the dusty mirror, a stranger staring back, eyes shadowed and weary. He turned away, unable to bear the sight. He was stuck. He knew it. The thought sat in his chest like a rock.

His father knocked softly on the door, then poked his head in. "Dinner's ready, son." The easy kindness in his father's voice only deepened his unease.

Emotion: brooding

Cluster: Sadness / Despair
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.60

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.749
😞0.329
그의0.299
un0.273
但他0.270
Suppressed:
de-0.917
la-0.603
a-0.369
l-0.335
her-0.330