diff --git a/src/features/phone_esm/straw/main.py b/src/features/phone_esm/straw/main.py
index cc7131e8..e3ff1aca 100644
--- a/src/features/phone_esm/straw/main.py
+++ b/src/features/phone_esm/straw/main.py
@@ -1,11 +1,15 @@
 import pandas as pd
 
+from esm_preprocess import QUESTIONNAIRE_IDS
+
 
 def straw_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs):
     esm_data = pd.read_csv(sensor_data_files["sensor_data"])
     requested_features = provider["FEATURES"]
     # name of the features this function can compute
+    requested_scales = provider["SCALES"]
     base_features_names = ["PANAS_positive_affect", "PANAS_negative_affect", "JCQ_job_demand", "JCQ_job_control", "JCQ_supervisor_support", "JCQ_coworker_support"]
+    #TODO Check valid questionnaire and feature names.
     # the subset of requested features this function can compute
     features_to_compute = list(set(requested_features) & set(base_features_names))
     esm_features = pd.DataFrame(columns=["local_segment"] + features_to_compute)
@@ -15,8 +19,11 @@ def straw_features(sensor_data_files, time_segment, provider, filter_data_by_seg
         if not esm_data.empty:
             esm_features = pd.DataFrame()
 
-            esm_features["mean"] = esm_data.groupby(["local_segment"])["esm_user_score"].mean()
-            #TODO Create the column esm_user_score in esm_clean. Currently, this is only done when reversing.
+            for scale in requested_scales:
+                questionnaire_id = QUESTIONNAIRE_IDS[scale]
+                mask = esm_data["questionnaire_id"] == questionnaire_id
+                esm_features[scale + "_mean"] = esm_data.loc[mask].groupby(["local_segment"])["esm_user_score"].mean()
+                #TODO Create the column esm_user_score in esm_clean. Currently, this is only done when reversing.
 
             esm_features = esm_features.reset_index()
     return esm_features