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 fire crackled merrily in the hearth, casting dancing shadows on the walls. He stretched out on the rug, the soft wool a comforting caress against his skin. The scent of pine and woodsmoke mingled in the air, creating a cocoon of warmth.

A sudden, melodic string of syllables broke the quiet. He looked up, his gaze drawn to her. She was sitting at the table, a book open in front of her, her face illuminated by the flickering flames.

"Ich liebe dich, mein Schatz," she said, her voice soft but sure. He felt a soft, pleasant ache in his chest.

Emotion: safe

Cluster: Calm / Serenity
PC1 (Valence): 1.86 Positive
PC2 (Disposition): -2.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
soon0.402
affectionately0.357
disfrut0.329
необходи0.325
🥰0.317
Suppressed:
S-0.474
C-0.416
L-0.408
worse-0.379
even-0.370