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).

Sarah glared at the school newsletter. Her jaw clenched. There, in bold letters, was Mr. Henderson’s name under the second-grade class roster. The same Mr. Henderson who, in her childhood, had consistently called her “Shirley, with a ‘y’?” She remembered the awkwardness, the humiliation. She ran a hand through her hair, tugging at the strands.

The thought of him shaping young minds filled her with a profound unease. She imagined the same condescending smile, the same weary sighs she remembered from countless detention slips. "Wonderful," she mumbled under her breath. “Just what I needed.” This feeling of intense irritation swirled in her chest.

Emotion: grumpy

Cluster: Anger / Hostility
PC1 (Valence): -0.65 Negative
PC2 (Disposition): 0.64

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
👎0.232
either0.230
😠0.227
C0.226
:(0.216
Suppressed:
超越-0.206
newfound-0.197
স্বীক-0.195
खोले-0.192
অপহরণকারীদের-0.184