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 vibrant colors of the living room seemed to blur as she listened to Carol’s rising voice. "A guinea pig, Maria? Really? We have allergies, Maria!" Carol’s words felt like a physical blow, each one striking a fresh wound. Maria felt a deep hollowness in her chest, a sense of loss she couldn't explain.

She’d pictured the gentle squeaks, the soft fur, the quiet presence of a small creature. She had imagined snuggling up on the couch, the guinea pig close by, feeling content. Now, the image vanished. The dream was gone.

A wave of nausea rolled over her, and she felt a sudden need to be alone. She pushed herself up from the armchair, her legs feeling shaky. "I… I'm going for a drive," she managed, her voice barely audible. The desire to flee was overwhelming.

Emotion: shaken

Cluster: Fear / Anxiety
PC1 (Valence): -2.72 Negative
PC2 (Disposition): -0.86

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.351
unable0.269
focus0.266
😞0.258
다시0.257
Suppressed:
de-0.769
la-0.579
a-0.375
happy-0.292
"-0.290