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 late afternoon sun warmed Elara's face as she strolled along the familiar path. A gentle breeze rustled through the leaves, a symphony she'd always loved. Her hands were clasped loosely behind her back, her shoulders relaxed. She was humming a tuneless melody, eyes scanning the familiar landscape of her childhood.

She rounded the bend and stopped, a soft gasp escaping her lips. Where a proud oak had once stood, a yawning emptiness remained. The ground was churned earth, the scent of fresh cut wood a stark contrast to the familiar fragrance of pine needles and damp soil.

Her fingers tightened on each other, a flicker of irritation crossing her face. "Blast," she muttered under her breath, a touch of annoyance in her voice. The quietness felt tainted, as if a song had stopped mid-note.

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