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 silence of the attic was almost deafening. He cleared his throat, the sound unusually loud in the stillness. He had expected junk. Instead, he had found… *artifacts*.

A collection of antique dolls, their porcelain faces staring blankly ahead. A dusty, leather-bound diary, its pages filled with elegant, looping handwriting. A small, tarnished silver locket. He felt a compulsion to leave, to get away from these silent sentinels of the past.

He backed away slowly, as if afraid to disturb some unseen presence. Each object felt like a direct intrusion into his quiet existence. He felt… exposed. Vulnerable.

Emotion: rattled

Cluster: Fear / Anxiety
PC1 (Valence): -2.29 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.264
😣0.261
worse0.256
😞0.248
😖0.247
Suppressed:
de-0.571
la-0.414
a-0.377
happy-0.259
enthusi-0.234