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).

Rain lashed against the windows of the venue, mirroring the tempest inside Leo. He hunched further into the shadows, the corner of the room offering a small measure of solace. The wedding, vibrant and joyous, felt like a movie he was forced to watch, a film he wasn't cast in. He watched everyone else, laughing, dancing, seemingly unburdened.

He caught a glimpse of Sarah across the dance floor. Her dark hair was pulled back, revealing a profile he knew intimately. She was smiling, laughing, her hand resting on the arm of a man Leo had never seen before. A fresh wave of something cold settled in his stomach.

He turned away, pretending to examine the floral arrangements, but every sense was hyper-aware of her presence. The music, a lively pop song, felt like a cruel joke. He slipped out of the room, into the hallway, seeking a pocket of silence, a space where the noise of the wedding couldn't reach him.

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
👏-0.251
sonra-0.240
aud-0.240