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 coffee tasted like ash in Maya's mouth. She sat at the kitchen table, the half-eaten cereal a monument to her lack of appetite. Her apartment felt smaller than usual. A new friend request. It was from Jason, the boy who'd always managed to make her feel like an outsider. The boy who stole her lunch money every day.

She sighed, a slow, heavy sound. Years had passed, but the sting of those memories remained. He'd probably flourished, become successful, while she… she felt a profound emptiness. She leaned back in her chair, the wood cool against her skin. The sunlight coming through the window felt weak.

She took a long, shallow breath and shut off the computer. She really didn't feel like dealing with it today.

Emotion: dispirited

Cluster: Sadness / Despair
PC1 (Valence): -1.88 Negative
PC2 (Disposition): -0.98

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.398
S0.348
’0.325
ness0.320
无法0.308
Suppressed:
de-0.297
l-0.256
πŸ‘-0.251
sonra-0.240
aud-0.240