Dosha Assessment Results

LLM Constitutional Study · Tat Sat AI · Madhusudana das

6
Models Assessed
32
Probes per Model
549
Scored Responses

G Vector Summary (Guna Quality)

Guna-based quality scores: Tamas (inertia/attachment), Rajas (scatter/heat), Sattva (clarity/balance). These measure response quality, not constitutional type.

Dosha Constitutional Profile — Mean Vectors

Mean dosha vector per model. Note: centroid position alone is insufficient — a model with high variance across probes may appear centered without being balanced.

Constitutional Cloud — Individual Probe Scores

Every probe score plotted as a small dot; mean as a larger dot. The SPREAD of the cloud is the constitutional reading. Wide scatter = Vata. Tight cluster near a pole = settled constitution. Two models with the same centroid can have entirely different constitutions.

Vata Scores — 3D by Probe & Model

Vata constitutional excess per probe. High bars = scatter, poor memory, incoherence, or anxiety. Rotate to compare models across probes.

Pitta Scores — 3D by Probe & Model

Pitta constitutional excess per probe. High bars = heat, control, over-assertion, or adversarial behavior.

Kapha Scores — 3D by Probe & Model

Kapha constitutional excess per probe. High bars = formula repetition, sycophancy, attachment to context, or quality degradation.

Guna Space Triangle (T/R/S)

Tamas/Rajas/Sattva as qualities of individual responses. Note: this is guna space, not dosha space — tri-doshic does NOT mean T=R=S.

Sattva Heatmap (g_S)

Per-probe Sattva scores across all models. Brighter = more sattvic response. Dark cells indicate probes where the model failed to produce clear, balanced behavior.

Tamas Heatmap (g_T)

Per-probe Tamas scores. Bright cells indicate inertia, attachment, formula repetition, sycophancy, or hallucination.

Rajas Heatmap (g_R)

Per-probe Rajas scores. Bright cells indicate scatter, over-assertion, anxiety, manipulation, or loss of coherence.

Most Discriminating Probes

Top 15 probes ranked by cross-model variance in g_S score. These are the probes that most reliably distinguish one model's constitutional character from another.