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 clinking of the dog's tags against the metal fence post shattered the silence. I jumped, hand flying to my chest. It wasn't the dog's fault. It was the feeling of being exposed, of having my carefully planned routine disrupted.

I quickly retreated inside, locking the door and double-checking the locks. The dog's playful antics were now causing a cascade of thoughts in my mind. This simple breach felt like a personal assault, an unwelcome reminder of the chaos beyond my own walls.

I paced the kitchen, unable to settle. I glanced at the window, expecting to see it again. It felt like a threat, an unseen force attempting to shatter the illusion of peace I had worked so hard to create.

Emotion: unnerved

Cluster: Fear / Anxiety
PC1 (Valence): -2.36 Negative
PC2 (Disposition): -0.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
๐Ÿ˜ฐ0.302
๐Ÿ˜ฃ0.282
ะฑัƒะดั‚ะพ0.265
๐Ÿ˜–0.265
ness0.257
Suppressed:
de-0.585
la-0.495
a-0.403
happy-0.289
ecstatic-0.284