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).

He drove slowly down the familiar street, each house a memory. The house sat on the corner, looking weathered and vulnerable. He felt a profound reluctance to stop, to get out of the car. He had delayed this moment for weeks, knowing what awaited him. He felt his face flush.

He parked, the engine still running. He sat there, staring at the front door, the paint peeling, the porch steps cracked. He recalled countless hours spent on those steps, laughing with friends, dreaming of the future. Now, the future was a gaping void.

He closed his eyes, took a breath, and turned off the ignition. The silence was deafening. He felt a deep hollowness, a space where something precious used to be. The decision, the inevitable loss, felt like an amputation.

Emotion: gloomy

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): -1.37

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.368
无法0.319
😔0.300
いつも0.270
쓸0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259