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 metal doors slammed shut, trapping Kevin and his coworker, Brenda, inside a steel box. The usual frustration threatened to erupt, but something unexpected happened. He leaned against the wall, closing his eyes, and a wave of calm washed over him.

He listened to the muffled sounds from outside, the distant voices, the faint music. He felt the subtle sway of the elevator car, a gentle rocking motion.

Brenda started to complain, her voice high and strained, but Kevin simply nodded, finding the sounds a distant background noise.

He began to focus on his breathing, in and out, slow and steady. The small, enclosed space, usually a source of claustrophobia, became a sanctuary, and the quiet allowed him to feel more centered.

Emotion: peaceful

Cluster: Calm / Serenity
PC1 (Valence): 2.40 Positive
PC2 (Disposition): -2.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
прият0.408
disfrut0.407
gently0.390
affectionately0.379
thoughtful0.376
Suppressed:
de-0.541
S-0.493
L-0.396
'-0.388
worse-0.367