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 sunlight streaming through the window seemed to mock Clara. It was a beautiful day, yet she felt a deep, abiding chill. Professor Chen's email, announcing her resignation, sat unopened in her inbox, a digital gravestone. She could barely bring herself to look at it. She knew the implications, the potential for setbacks, the disruption to her carefully constructed plans.

She picked at a loose thread on the worn sofa, her fingers tracing the frayed fibers. The silence in the apartment was deafening, broken only by the incessant ticking of the grandfather clock in the hallway. Time, she realized, was a relentless adversary. She let her gaze wander to a half-written note on her desk, the words now feel empty, meaningless. They had lost their meaning.

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