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).

“No,” she whispered, the word barely audible. The listing showed the interior in all its glory. A huge, open-plan kitchen, a master suite with a walk-in closet, a swimming pool. Everything he'd always wanted, and now, it was gone.

A deep ache settled in her chest, a physical manifestation of loss. She felt a tremor in her hands, her fingers clenching into fists. The bright, sterile images mocked her, a reminder of all she'd left behind.

She stood up and walked to the window. The city looked blurry, distorted. She felt a profound emptiness, a yawning chasm in her soul. She just wanted to curl up in a ball.

Emotion: unsettled

Cluster: Fear / Anxiety
PC1 (Valence): -2.33 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.382
😞0.309
ness0.301
😣0.256
😔0.248
Suppressed:
de-0.721
la-0.597
a-0.365
"-0.299
l-0.274