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 morning sun streamed through the office window, illuminating dust motes dancing in the air. Sarah hummed a jaunty tune as she filed paperwork, a little skip in her step she hadn't felt in weeks. Her coffee tasted particularly good this morning, the aroma filling her with a sense of well-being. A company-wide email pinged on her computer. She clicked it open, a grin spreading across her face as she read the subject line: “Important Announcement.”

Her heart quickened. She knew what this meant. The whispers had been circulating for months, the rumors of a potential acquisition. Now, it was finally happening. A new chapter! This meant a chance for growth, for new opportunities, and a fresh start. She leaned back in her chair, a wide smile playing on her lips. She could practically feel the excitement bubbling inside her.

Emotion: joyful

Cluster: Positive / Joy
PC1 (Valence): 3.96 Positive
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.615
de0.600
!0.572
excitedly0.552
enthusi0.533
Suppressed:
S-0.893
ness-0.513
😞-0.470
😣-0.337
L-0.334