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).

Rain lashed against the window, mirroring the storm inside him. “So, the first thing you need to know,” he began, his voice barely a whisper, “is that this job… it’s a lot.” He didn't look at Maria, the person he had to train. He focused on the droplets tracing patterns on the glass.

Each time she asked a question, a sharp pang shot through him. He found himself answering in short, clipped sentences, avoiding eye contact. He felt as if a part of himself was being stripped away, piece by piece.

He crossed his arms, the action a self-protective gesture. He didn't want to explain how he felt. He wished she would just leave. The sound of her clicking mouse became an annoying percussion.

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